import random
import math
import operator
+import hashlib
+import binascii
+import urllib
from .utils import *
def _request_webpage(self, url_or_request, video_id, note=None, errnote=None):
""" Returns the response handle """
if note is None:
- note = u'Downloading video webpage'
- if note is not False:
+ self.report_download_webpage(video_id)
+ elif note is not False:
self.to_screen(u'%s: %s' % (video_id, note))
try:
return compat_urllib_request.urlopen(url_or_request)
errnote = u'Unable to download webpage'
raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2])
- def _download_webpage(self, url_or_request, video_id, note=None, errnote=None):
- """ Returns the data of the page as a string """
+ def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
+ """ Returns a tuple (page content as string, URL handle) """
urlh = self._request_webpage(url_or_request, video_id, note, errnote)
content_type = urlh.headers.get('Content-Type', '')
m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
self.to_screen(u'Dumping request to ' + url)
dump = base64.b64encode(webpage_bytes).decode('ascii')
self._downloader.to_screen(dump)
- return webpage_bytes.decode(encoding, 'replace')
+ content = webpage_bytes.decode(encoding, 'replace')
+ return (content, urlh)
+
+ def _download_webpage(self, url_or_request, video_id, note=None, errnote=None):
+ """ Returns the data of the page as a string """
+ return self._download_webpage_handle(url_or_request, video_id, note, errnote)[0]
def to_screen(self, msg):
"""Print msg to screen, prefixing it with '[ie_name]'"""
video_info['title'] = playlist_title
return video_info
+ def _search_regex(self, pattern, string, name, default=None, fatal=True, flags=0):
+ """
+ Perform a regex search on the given string, using a single or a list of
+ patterns returning the first matching group.
+ In case of failure return a default value or raise a WARNING or a
+ ExtractorError, depending on fatal, specifying the field name.
+ """
+ if isinstance(pattern, (str, compat_str, compiled_regex_type)):
+ mobj = re.search(pattern, string, flags)
+ else:
+ for p in pattern:
+ mobj = re.search(p, string, flags)
+ if mobj: break
+
+ if sys.stderr.isatty() and os.name != 'nt':
+ _name = u'\033[0;34m%s\033[0m' % name
+ else:
+ _name = name
+
+ if mobj:
+ # return the first matching group
+ return next(g for g in mobj.groups() if g is not None)
+ elif default is not None:
+ return default
+ elif fatal:
+ raise ExtractorError(u'Unable to extract %s' % _name)
+ else:
+ self._downloader.report_warning(u'unable to extract %s; '
+ u'please report this issue on GitHub.' % _name)
+ return None
+
+ def _html_search_regex(self, pattern, string, name, default=None, fatal=True, flags=0):
+ """
+ Like _search_regex, but strips HTML tags and unescapes entities.
+ """
+ res = self._search_regex(pattern, string, name, default, fatal, flags)
+ if res:
+ return clean_html(res).strip()
+ else:
+ return res
+
+class SearchInfoExtractor(InfoExtractor):
+ """
+ Base class for paged search queries extractors.
+ They accept urls in the format _SEARCH_KEY(|all|[0-9]):{query}
+ Instances should define _SEARCH_KEY and _MAX_RESULTS.
+ """
+
+ @classmethod
+ def _make_valid_url(cls):
+ return r'%s(?P<prefix>|[1-9][0-9]*|all):(?P<query>[\s\S]+)' % cls._SEARCH_KEY
+
+ @classmethod
+ def suitable(cls, url):
+ return re.match(cls._make_valid_url(), url) is not None
+
+ def _real_extract(self, query):
+ mobj = re.match(self._make_valid_url(), query)
+ if mobj is None:
+ raise ExtractorError(u'Invalid search query "%s"' % query)
+
+ prefix = mobj.group('prefix')
+ query = mobj.group('query')
+ if prefix == '':
+ return self._get_n_results(query, 1)
+ elif prefix == 'all':
+ return self._get_n_results(query, self._MAX_RESULTS)
+ else:
+ n = int(prefix)
+ if n <= 0:
+ raise ExtractorError(u'invalid download number %s for query "%s"' % (n, query))
+ elif n > self._MAX_RESULTS:
+ self._downloader.report_warning(u'%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n))
+ n = self._MAX_RESULTS
+ return self._get_n_results(query, n)
+
+ def _get_n_results(self, query, n):
+ """Get a specified number of results for a query"""
+ raise NotImplementedError("This method must be implemented by sublclasses")
+
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
([0-9A-Za-z_-]+) # here is it! the YouTube video ID
(?(1).+)? # if we found the ID, everything can follow
$"""
- _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
+ _LANG_URL = r'https://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
_NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
return (u'Did not fetch video subtitles', None, None)
return (None, sub_lang, sub)
+ def _request_automatic_caption(self, video_id, webpage):
+ """We need the webpage for getting the captions url, pass it as an
+ argument to speed up the process."""
+ sub_lang = self._downloader.params.get('subtitleslang')
+ sub_format = self._downloader.params.get('subtitlesformat')
+ self.to_screen(u'%s: Looking for automatic captions' % video_id)
+ mobj = re.search(r';ytplayer.config = ({.*?});', webpage)
+ err_msg = u'Couldn\'t find automatic captions for "%s"' % sub_lang
+ if mobj is None:
+ return [(err_msg, None, None)]
+ player_config = json.loads(mobj.group(1))
+ try:
+ args = player_config[u'args']
+ caption_url = args[u'ttsurl']
+ timestamp = args[u'timestamp']
+ params = compat_urllib_parse.urlencode({
+ 'lang': 'en',
+ 'tlang': sub_lang,
+ 'fmt': sub_format,
+ 'ts': timestamp,
+ 'kind': 'asr',
+ })
+ subtitles_url = caption_url + '&' + params
+ sub = self._download_webpage(subtitles_url, video_id, u'Downloading automatic captions')
+ return [(None, sub_lang, sub)]
+ except KeyError:
+ return [(err_msg, None, None)]
+
def _extract_subtitle(self, video_id):
"""
Return a list with a tuple:
# Log in
login_form_strs = {
- u'continue': u'http://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
+ u'continue': u'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
u'Email': username,
u'GALX': galx,
u'Passwd': password,
self.report_age_confirmation()
age_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to confirm age: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err))
def _extract_id(self, url):
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(2)
return video_id
# Extract original video URL from URL with redirection, like age verification, using next_url parameter
mobj = re.search(self._NEXT_URL_RE, url)
if mobj:
- url = 'http://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
+ url = 'https://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
video_id = self._extract_id(url)
# Get video webpage
self.report_video_webpage_download(video_id)
- url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id
+ url = 'https://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id
request = compat_urllib_request.Request(url)
try:
video_webpage_bytes = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to download video webpage: %s' % compat_str(err))
video_webpage = video_webpage_bytes.decode('utf-8', 'ignore')
break
if 'token' not in video_info:
if 'reason' in video_info:
- self._downloader.report_error(u'YouTube said: %s' % video_info['reason'][0])
+ raise ExtractorError(u'YouTube said: %s' % video_info['reason'][0])
else:
- self._downloader.report_error(u'"token" parameter not in video info for unknown reason')
- return
+ raise ExtractorError(u'"token" parameter not in video info for unknown reason')
# Check for "rental" videos
if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
- self._downloader.report_error(u'"rental" videos not supported')
- return
+ raise ExtractorError(u'"rental" videos not supported')
# Start extracting information
self.report_information_extraction(video_id)
# uploader
if 'author' not in video_info:
- self._downloader.report_error(u'unable to extract uploader name')
- return
+ raise ExtractorError(u'Unable to extract uploader name')
video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0])
# uploader_id
# title
if 'title' not in video_info:
- self._downloader.report_error(u'unable to extract video title')
- return
+ raise ExtractorError(u'Unable to extract video title')
video_title = compat_urllib_parse.unquote_plus(video_info['title'][0])
# thumbnail image
mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
if mobj is not None:
upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
- format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y']
- for expression in format_expressions:
- try:
- upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
- except:
- pass
+ upload_date = unified_strdate(upload_date)
# description
video_description = get_element_by_id("eow-description", video_webpage)
if video_subtitles:
(sub_error, sub_lang, sub) = video_subtitles[0]
if sub_error:
- self._downloader.report_error(sub_error)
+ # We try with the automatic captions
+ video_subtitles = self._request_automatic_caption(video_id, video_webpage)
+ (sub_error_auto, sub_lang, sub) = video_subtitles[0]
+ if sub is not None:
+ pass
+ else:
+ # We report the original error
+ self._downloader.report_error(sub_error)
if self._downloader.params.get('allsubtitles', False):
video_subtitles = self._extract_all_subtitles(video_id)
self.report_rtmp_download()
video_url_list = [(None, video_info['conn'][0])]
elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1:
- url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
- url_data = [compat_parse_qs(uds) for uds in url_data_strs]
- url_data = [ud for ud in url_data if 'itag' in ud and 'url' in ud]
- url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data)
+ url_map = {}
+ for url_data_str in video_info['url_encoded_fmt_stream_map'][0].split(','):
+ url_data = compat_parse_qs(url_data_str)
+ if 'itag' in url_data and 'url' in url_data:
+ url = url_data['url'][0] + '&signature=' + url_data['sig'][0]
+ if not 'ratebypass' in url: url += '&ratebypass=yes'
+ url_map[url_data['itag'][0]] = url
format_limit = self._downloader.params.get('format_limit', None)
available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
_FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
IE_NAME = u'metacafe'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
def report_disclaimer(self):
"""Report disclaimer retrieval."""
self.to_screen(u'Retrieving disclaimer')
self.report_disclaimer()
disclaimer = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to retrieve disclaimer: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err))
# Confirm age
disclaimer_form = {
self.report_age_confirmation()
disclaimer = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to confirm age: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err))
def _real_extract(self, url):
# Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(1)
else:
mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
if mobj is None:
- self._downloader.report_error(u'unable to extract media URL')
- return
+ raise ExtractorError(u'Unable to extract media URL')
vardict = compat_parse_qs(mobj.group(1))
if 'mediaData' not in vardict:
- self._downloader.report_error(u'unable to extract media URL')
- return
+ raise ExtractorError(u'Unable to extract media URL')
mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
if mobj is None:
- self._downloader.report_error(u'unable to extract media URL')
- return
+ raise ExtractorError(u'Unable to extract media URL')
mediaURL = mobj.group('mediaURL').replace('\\/', '/')
video_extension = mediaURL[-3:]
video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
if mobj is None:
- self._downloader.report_error(u'unable to extract title')
- return
+ raise ExtractorError(u'Unable to extract title')
video_title = mobj.group(1).decode('utf-8')
mobj = re.search(r'submitter=(.*?);', webpage)
if mobj is None:
- self._downloader.report_error(u'unable to extract uploader nickname')
- return
+ raise ExtractorError(u'Unable to extract uploader nickname')
video_uploader = mobj.group(1)
return [{
'ext': video_extension.decode('utf-8'),
}]
-
class DailymotionIE(InfoExtractor):
"""Information Extractor for Dailymotion"""
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
IE_NAME = u'dailymotion'
- _WORKING = False
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
def _real_extract(self, url):
# Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(1).split('_')[0].split('?')[0]
self.report_extraction(video_id)
mobj = re.search(r'\s*var flashvars = (.*)', webpage)
if mobj is None:
- self._downloader.report_error(u'unable to extract media URL')
- return
+ raise ExtractorError(u'Unable to extract media URL')
flashvars = compat_urllib_parse.unquote(mobj.group(1))
for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']:
self.to_screen(u'Using %s' % key)
break
else:
- self._downloader.report_error(u'unable to extract video URL')
- return
+ raise ExtractorError(u'Unable to extract video URL')
mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars)
if mobj is None:
- self._downloader.report_error(u'unable to extract video URL')
- return
+ raise ExtractorError(u'Unable to extract video URL')
video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/')
mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
if mobj is None:
- self._downloader.report_error(u'unable to extract title')
- return
+ raise ExtractorError(u'Unable to extract title')
video_title = unescapeHTML(mobj.group('title'))
video_uploader = None
class PhotobucketIE(InfoExtractor):
"""Information extractor for photobucket.com."""
- _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
+ # TODO: the original _VALID_URL was:
+ # r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
+ # Check if it's necessary to keep the old extracion process
+ _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
IE_NAME = u'photobucket'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
def _real_extract(self, url):
# Extract id from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'Invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
- video_id = mobj.group(1)
+ video_id = mobj.group('id')
- video_extension = 'flv'
+ video_extension = mobj.group('ext')
# Retrieve video webpage to extract further information
- request = compat_urllib_request.Request(url)
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err))
- return
+ webpage = self._download_webpage(url, video_id)
# Extract URL, uploader, and title from webpage
self.report_extraction(video_id)
- mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
- if mobj is None:
- self._downloader.report_error(u'unable to extract media URL')
- return
- mediaURL = compat_urllib_parse.unquote(mobj.group(1))
+ # We try first by looking the javascript code:
+ mobj = re.search(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (?P<json>.*?)\);', webpage)
+ if mobj is not None:
+ info = json.loads(mobj.group('json'))
+ return [{
+ 'id': video_id,
+ 'url': info[u'downloadUrl'],
+ 'uploader': info[u'username'],
+ 'upload_date': datetime.date.fromtimestamp(info[u'creationDate']).strftime('%Y%m%d'),
+ 'title': info[u'title'],
+ 'ext': video_extension,
+ 'thumbnail': info[u'thumbUrl'],
+ }]
- video_url = mediaURL
+ # We try looking in other parts of the webpage
+ video_url = self._search_regex(r'<link rel="video_src" href=".*\?file=([^"]+)" />',
+ webpage, u'video URL')
mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
if mobj is None:
- self._downloader.report_error(u'unable to extract title')
- return
+ raise ExtractorError(u'Unable to extract title')
video_title = mobj.group(1).decode('utf-8')
-
video_uploader = mobj.group(2).decode('utf-8')
return [{
class YahooIE(InfoExtractor):
- """Information extractor for video.yahoo.com."""
-
- _WORKING = False
- # _VALID_URL matches all Yahoo! Video URLs
- # _VPAGE_URL matches only the extractable '/watch/' URLs
- _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
- _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
- IE_NAME = u'video.yahoo'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
+ """Information extractor for screen.yahoo.com."""
+ _VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P<id>\d*?)\.html'
- def _real_extract(self, url, new_video=True):
- # Extract ID from URL
+ def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'Invalid URL: %s' % url)
- return
-
- video_id = mobj.group(2)
- video_extension = 'flv'
-
- # Rewrite valid but non-extractable URLs as
- # extractable English language /watch/ URLs
- if re.match(self._VPAGE_URL, url) is None:
- request = compat_urllib_request.Request(url)
- try:
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err))
- return
-
- mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
- if mobj is None:
- self._downloader.report_error(u'Unable to extract id field')
- return
- yahoo_id = mobj.group(1)
-
- mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
- if mobj is None:
- self._downloader.report_error(u'Unable to extract vid field')
- return
- yahoo_vid = mobj.group(1)
-
- url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
- return self._real_extract(url, new_video=False)
-
- # Retrieve video webpage to extract further information
- request = compat_urllib_request.Request(url)
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err))
- return
-
- # Extract uploader and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r'<meta name="title" content="(.*)" />', webpage)
- if mobj is None:
- self._downloader.report_error(u'unable to extract video title')
- return
- video_title = mobj.group(1).decode('utf-8')
-
- mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
- if mobj is None:
- self._downloader.report_error(u'unable to extract video uploader')
- return
- video_uploader = mobj.group(1).decode('utf-8')
-
- # Extract video thumbnail
- mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage)
- if mobj is None:
- self._downloader.report_error(u'unable to extract video thumbnail')
- return
- video_thumbnail = mobj.group(1).decode('utf-8')
-
- # Extract video description
- mobj = re.search(r'<meta name="description" content="(.*)" />', webpage)
- if mobj is None:
- self._downloader.report_error(u'unable to extract video description')
- return
- video_description = mobj.group(1).decode('utf-8')
- if not video_description:
- video_description = 'No description available.'
-
- # Extract video height and width
- mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
- if mobj is None:
- self._downloader.report_error(u'unable to extract video height')
- return
- yv_video_height = mobj.group(1)
-
- mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage)
- if mobj is None:
- self._downloader.report_error(u'unable to extract video width')
- return
- yv_video_width = mobj.group(1)
-
- # Retrieve video playlist to extract media URL
- # I'm not completely sure what all these options are, but we
- # seem to need most of them, otherwise the server sends a 401.
- yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
- yv_bitrate = '700' # according to Wikipedia this is hard-coded
- request = compat_urllib_request.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
- '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
- '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err))
- return
-
- # Extract media URL from playlist XML
- mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage)
- if mobj is None:
- self._downloader.report_error(u'Unable to extract media URL')
- return
- video_url = compat_urllib_parse.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
- video_url = unescapeHTML(video_url)
-
- return [{
- 'id': video_id.decode('utf-8'),
- 'url': video_url,
- 'uploader': video_uploader,
- 'upload_date': None,
- 'title': video_title,
- 'ext': video_extension.decode('utf-8'),
- 'thumbnail': video_thumbnail.decode('utf-8'),
- 'description': video_description,
- }]
-
+ raise ExtractorError(u'Invalid URL: %s' % url)
+ video_id = mobj.group('id')
+ webpage = self._download_webpage(url, video_id)
+ m_id = re.search(r'YUI\.namespace\("Media"\)\.CONTENT_ID = "(?P<new_id>.+?)";', webpage)
+
+ if m_id is None:
+ # TODO: Check which url parameters are required
+ info_url = 'http://cosmos.bcst.yahoo.com/rest/v2/pops;lmsoverride=1;outputformat=mrss;cb=974419660;id=%s;rd=news.yahoo.com;datacontext=mdb;lg=KCa2IihxG3qE60vQ7HtyUy' % video_id
+ webpage = self._download_webpage(info_url, video_id, u'Downloading info webpage')
+ info_re = r'''<title><!\[CDATA\[(?P<title>.*?)\]\]></title>.*
+ <description><!\[CDATA\[(?P<description>.*?)\]\]></description>.*
+ <media:pubStart><!\[CDATA\[(?P<date>.*?)\ .*\]\]></media:pubStart>.*
+ <media:content\ medium="image"\ url="(?P<thumb>.*?)"\ name="LARGETHUMB"
+ '''
+ self.report_extraction(video_id)
+ m_info = re.search(info_re, webpage, re.VERBOSE|re.DOTALL)
+ if m_info is None:
+ raise ExtractorError(u'Unable to extract video info')
+ video_title = m_info.group('title')
+ video_description = m_info.group('description')
+ video_thumb = m_info.group('thumb')
+ video_date = m_info.group('date')
+ video_date = datetime.datetime.strptime(video_date, '%m/%d/%Y').strftime('%Y%m%d')
+
+ # TODO: Find a way to get mp4 videos
+ rest_url = 'http://cosmos.bcst.yahoo.com/rest/v2/pops;element=stream;outputformat=mrss;id=%s;lmsoverride=1;bw=375;dynamicstream=1;cb=83521105;tech=flv,mp4;rd=news.yahoo.com;datacontext=mdb;lg=KCa2IihxG3qE60vQ7HtyUy' % video_id
+ webpage = self._download_webpage(rest_url, video_id, u'Downloading video url webpage')
+ m_rest = re.search(r'<media:content url="(?P<url>.*?)" path="(?P<path>.*?)"', webpage)
+ video_url = m_rest.group('url')
+ video_path = m_rest.group('path')
+ if m_rest is None:
+ raise ExtractorError(u'Unable to extract video url')
+
+ else: # We have to use a different method if another id is defined
+ long_id = m_id.group('new_id')
+ info_url = 'http://video.query.yahoo.com/v1/public/yql?q=SELECT%20*%20FROM%20yahoo.media.video.streams%20WHERE%20id%3D%22' + long_id + '%22%20AND%20format%3D%22mp4%2Cflv%22%20AND%20protocol%3D%22rtmp%2Chttp%22%20AND%20plrs%3D%2286Gj0vCaSzV_Iuf6hNylf2%22%20AND%20acctid%3D%22389%22%20AND%20plidl%3D%22%22%20AND%20pspid%3D%22792700001%22%20AND%20offnetwork%3D%22false%22%20AND%20site%3D%22ivy%22%20AND%20lang%3D%22en-US%22%20AND%20region%3D%22US%22%20AND%20override%3D%22none%22%3B&env=prod&format=json&callback=YUI.Env.JSONP.yui_3_8_1_1_1368368376830_335'
+ webpage = self._download_webpage(info_url, video_id, u'Downloading info json')
+ json_str = re.search(r'YUI.Env.JSONP.yui.*?\((.*?)\);', webpage).group(1)
+ info = json.loads(json_str)
+ res = info[u'query'][u'results'][u'mediaObj'][0]
+ stream = res[u'streams'][0]
+ video_path = stream[u'path']
+ video_url = stream[u'host']
+ meta = res[u'meta']
+ video_title = meta[u'title']
+ video_description = meta[u'description']
+ video_thumb = meta[u'thumbnail']
+ video_date = None # I can't find it
+
+ info_dict = {
+ 'id': video_id,
+ 'url': video_url,
+ 'play_path': video_path,
+ 'title':video_title,
+ 'description': video_description,
+ 'thumbnail': video_thumb,
+ 'upload_date': video_date,
+ 'ext': 'flv',
+ }
+ return info_dict
class VimeoIE(InfoExtractor):
"""Information extractor for vimeo.com."""
# _VALID_URL matches Vimeo URLs
- _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)'
+ _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)'
IE_NAME = u'vimeo'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
def _real_extract(self, url, new_video=True):
# Extract ID from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'Invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('id')
if not mobj.group('proto'):
url = 'https://' + url
- if mobj.group('direct_link'):
+ if mobj.group('direct_link') or mobj.group('pro'):
url = 'https://vimeo.com/' + video_id
# Retrieve video webpage to extract further information
request = compat_urllib_request.Request(url, None, std_headers)
- try:
- self.report_download_webpage(video_id)
- webpage_bytes = compat_urllib_request.urlopen(request).read()
- webpage = webpage_bytes.decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err))
- return
+ webpage = self._download_webpage(request, video_id)
# Now we begin extracting as much information as we can from what we
# retrieved. First we extract the information common to all extractors,
config = webpage.split(' = {config:')[1].split(',assets:')[0]
config = json.loads(config)
except:
- self._downloader.report_error(u'unable to extract info section')
- return
+ if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
+ raise ExtractorError(u'The author has restricted the access to this video, try with the "--referer" option')
+ else:
+ raise ExtractorError(u'Unable to extract info section')
# Extract title
video_title = config["video"]["title"]
# Extract uploader and uploader_id
video_uploader = config["video"]["owner"]["name"]
- video_uploader_id = config["video"]["owner"]["url"].split('/')[-1]
+ video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None
# Extract video thumbnail
video_thumbnail = config["video"]["thumbnail"]
self.to_screen(u'%s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality))
break
else:
- self._downloader.report_error(u'no known codec found')
- return
+ raise ExtractorError(u'No known codec found')
video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
%(video_id, sig, timestamp, video_quality, video_codec.upper())
IE_NAME = u'arte.tv'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
def fetch_webpage(self, url):
request = compat_urllib_request.Request(url)
try:
self.report_download_webpage(url)
webpage = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to retrieve video webpage: %s' % compat_str(err))
except ValueError as err:
- self._downloader.report_error(u'Invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
return webpage
def grep_webpage(self, url, regex, regexFlags, matchTuples):
info = {}
if mobj is None:
- self._downloader.report_error(u'Invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
for (i, key, err) in matchTuples:
if mobj.group(i) is None:
- self._downloader.report_error(err)
- return
+ raise ExtractorError(err)
else:
info[key] = mobj.group(i)
'id': info.get('id'),
'url': compat_urllib_parse.unquote(info.get('url')),
'uploader': u'arte.tv',
- 'upload_date': info.get('date'),
+ 'upload_date': unified_strdate(info.get('date')),
'title': info.get('title').decode('utf-8'),
'ext': u'mp4',
'format': u'NA',
_VALID_URL = r'.*'
IE_NAME = u'generic'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
def report_download_webpage(self, video_id):
"""Report webpage download."""
if not self._downloader.params.get('test', False):
self._downloader.report_warning(u'Falling back on generic information extractor.')
- self.to_screen(u'%s: Downloading webpage' % video_id)
+ super(GenericIE, self).report_download_webpage(video_id)
def report_following_redirect(self, new_url):
"""Report information extraction."""
opener.add_handler(handler())
response = opener.open(HeadRequest(url))
+ if response is None:
+ raise ExtractorError(u'Invalid URL protocol')
new_url = response.geturl()
if url == new_url:
except ValueError as err:
# since this is the last-resort InfoExtractor, if
# this error is thrown, it'll be thrown here
- self._downloader.report_error(u'Invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
self.report_extraction(video_id)
# Start with something easy: JW Player in SWFObject
# Broaden the search a little bit: JWPlayer JS loader
mobj = re.search(r'[^A-Za-z0-9]?file:\s*["\'](http[^\'"&]*)', webpage)
if mobj is None:
- self._downloader.report_error(u'Invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
# It's possible that one of the regexes
# matched, but returned an empty group:
if mobj.group(1) is None:
- self._downloader.report_error(u'Invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_url = compat_urllib_parse.unquote(mobj.group(1))
video_id = os.path.basename(video_url)
# and so on and so forth; it's just not practical
mobj = re.search(r'<title>(.*)</title>', webpage)
if mobj is None:
- self._downloader.report_error(u'unable to extract title')
- return
+ raise ExtractorError(u'Unable to extract title')
video_title = mobj.group(1)
# video uploader is domain name
mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
if mobj is None:
- self._downloader.report_error(u'unable to extract title')
- return
+ raise ExtractorError(u'Unable to extract title')
video_uploader = mobj.group(1)
return [{
}]
-class YoutubeSearchIE(InfoExtractor):
+class YoutubeSearchIE(SearchInfoExtractor):
"""Information Extractor for YouTube search queries."""
- _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+'
_API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc'
- _max_youtube_results = 1000
+ _MAX_RESULTS = 1000
IE_NAME = u'youtube:search'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
+ _SEARCH_KEY = 'ytsearch'
def report_download_page(self, query, pagenum):
"""Report attempt to download search page with given number."""
query = query.decode(preferredencoding())
self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
- def _real_extract(self, query):
- mobj = re.match(self._VALID_URL, query)
- if mobj is None:
- self._downloader.report_error(u'invalid search query "%s"' % query)
- return
-
- prefix, query = query.split(':')
- prefix = prefix[8:]
- query = query.encode('utf-8')
- if prefix == '':
- return self._get_n_results(query, 1)
- elif prefix == 'all':
- self._get_n_results(query, self._max_youtube_results)
- else:
- try:
- n = int(prefix)
- if n <= 0:
- self._downloader.report_error(u'invalid download number %s for query "%s"' % (n, query))
- return
- elif n > self._max_youtube_results:
- self._downloader.report_warning(u'ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
- n = self._max_youtube_results
- return self._get_n_results(query, n)
- except ValueError: # parsing prefix as integer fails
- return self._get_n_results(query, 1)
-
def _get_n_results(self, query, n):
"""Get a specified number of results for a query"""
try:
data = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download API page: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to download API page: %s' % compat_str(err))
api_response = json.loads(data)['data']
if not 'items' in api_response:
- self._downloader.report_error(u'[youtube] No video results')
- return
+ raise ExtractorError(u'[youtube] No video results')
new_ids = list(video['id'] for video in api_response['items'])
video_ids += new_ids
if len(video_ids) > n:
video_ids = video_ids[:n]
videos = [self.url_result('http://www.youtube.com/watch?v=%s' % id, 'Youtube') for id in video_ids]
- return videos
+ return self.playlist_result(videos, query)
-class GoogleSearchIE(InfoExtractor):
+class GoogleSearchIE(SearchInfoExtractor):
"""Information Extractor for Google Video search queries."""
- _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+'
- _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
- _VIDEO_INDICATOR = r'<a href="http://video\.google\.com/videoplay\?docid=([^"\&]+)'
- _MORE_PAGES_INDICATOR = r'class="pn" id="pnnext"'
- _max_google_results = 1000
+ _MORE_PAGES_INDICATOR = r'id="pnnext" class="pn"'
+ _MAX_RESULTS = 1000
IE_NAME = u'video.google:search'
+ _SEARCH_KEY = 'gvsearch'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_page(self, query, pagenum):
- """Report attempt to download playlist page with given number."""
- query = query.decode(preferredencoding())
- self.to_screen(u'query "%s": Downloading page %s' % (query, pagenum))
+ def _get_n_results(self, query, n):
+ """Get a specified number of results for a query"""
- def _real_extract(self, query):
- mobj = re.match(self._VALID_URL, query)
- if mobj is None:
- self._downloader.report_error(u'invalid search query "%s"' % query)
- return
+ res = {
+ '_type': 'playlist',
+ 'id': query,
+ 'entries': []
+ }
- prefix, query = query.split(':')
- prefix = prefix[8:]
- query = query.encode('utf-8')
- if prefix == '':
- self._download_n_results(query, 1)
- return
- elif prefix == 'all':
- self._download_n_results(query, self._max_google_results)
- return
- else:
- try:
- n = int(prefix)
- if n <= 0:
- self._downloader.report_error(u'invalid download number %s for query "%s"' % (n, query))
- return
- elif n > self._max_google_results:
- self._downloader.report_warning(u'gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
- n = self._max_google_results
- self._download_n_results(query, n)
- return
- except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
+ for pagenum in itertools.count(1):
+ result_url = u'http://www.google.com/search?tbm=vid&q=%s&start=%s&hl=en' % (compat_urllib_parse.quote_plus(query), pagenum*10)
+ webpage = self._download_webpage(result_url, u'gvsearch:' + query,
+ note='Downloading result page ' + str(pagenum))
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
+ for mobj in re.finditer(r'<h3 class="r"><a href="([^"]+)"', webpage):
+ e = {
+ '_type': 'url',
+ 'url': mobj.group(1)
+ }
+ res['entries'].append(e)
- video_ids = []
- pagenum = 0
+ if (pagenum * 10 > n) or not re.search(self._MORE_PAGES_INDICATOR, webpage):
+ return res
- while True:
- self.report_download_page(query, pagenum)
- result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum*10)
- request = compat_urllib_request.Request(result_url)
- try:
- page = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
- return
+class YahooSearchIE(SearchInfoExtractor):
+ """Information Extractor for Yahoo! Video search queries."""
- # Extract video identifiers
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- video_id = mobj.group(1)
- if video_id not in video_ids:
- video_ids.append(video_id)
- if len(video_ids) == n:
- # Specified n videos reached
- for id in video_ids:
- self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id])
- return
-
- if re.search(self._MORE_PAGES_INDICATOR, page) is None:
- for id in video_ids:
- self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id])
- return
+ _MAX_RESULTS = 1000
+ IE_NAME = u'screen.yahoo:search'
+ _SEARCH_KEY = 'yvsearch'
- pagenum = pagenum + 1
+ def _get_n_results(self, query, n):
+ """Get a specified number of results for a query"""
+ res = {
+ '_type': 'playlist',
+ 'id': query,
+ 'entries': []
+ }
+ for pagenum in itertools.count(0):
+ result_url = u'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30)
+ webpage = self._download_webpage(result_url, query,
+ note='Downloading results page '+str(pagenum+1))
+ info = json.loads(webpage)
+ m = info[u'm']
+ results = info[u'results']
+
+ for (i, r) in enumerate(results):
+ if (pagenum * 30) +i >= n:
+ break
+ mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r)
+ e = self.url_result('http://' + mobj.group('url'), 'Yahoo')
+ res['entries'].append(e)
+ if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1 )):
+ break
-class YahooSearchIE(InfoExtractor):
- """Information Extractor for Yahoo! Video search queries."""
-
- _WORKING = False
- _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+'
- _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
- _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
- _MORE_PAGES_INDICATOR = r'\s*Next'
- _max_yahoo_results = 1000
- IE_NAME = u'video.yahoo:search'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_page(self, query, pagenum):
- """Report attempt to download playlist page with given number."""
- query = query.decode(preferredencoding())
- self.to_screen(u'query "%s": Downloading page %s' % (query, pagenum))
-
- def _real_extract(self, query):
- mobj = re.match(self._VALID_URL, query)
- if mobj is None:
- self._downloader.report_error(u'invalid search query "%s"' % query)
- return
-
- prefix, query = query.split(':')
- prefix = prefix[8:]
- query = query.encode('utf-8')
- if prefix == '':
- self._download_n_results(query, 1)
- return
- elif prefix == 'all':
- self._download_n_results(query, self._max_yahoo_results)
- return
- else:
- try:
- n = int(prefix)
- if n <= 0:
- self._downloader.report_error(u'invalid download number %s for query "%s"' % (n, query))
- return
- elif n > self._max_yahoo_results:
- self._downloader.report_warning(u'yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
- n = self._max_yahoo_results
- self._download_n_results(query, n)
- return
- except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
-
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
-
- video_ids = []
- already_seen = set()
- pagenum = 1
-
- while True:
- self.report_download_page(query, pagenum)
- result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum)
- request = compat_urllib_request.Request(result_url)
- try:
- page = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
- return
-
- # Extract video identifiers
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- video_id = mobj.group(1)
- if video_id not in already_seen:
- video_ids.append(video_id)
- already_seen.add(video_id)
- if len(video_ids) == n:
- # Specified n videos reached
- for id in video_ids:
- self._downloader.download(['http://video.yahoo.com/watch/%s' % id])
- return
-
- if re.search(self._MORE_PAGES_INDICATOR, page) is None:
- for id in video_ids:
- self._downloader.download(['http://video.yahoo.com/watch/%s' % id])
- return
-
- pagenum = pagenum + 1
+ return res
class YoutubePlaylistIE(InfoExtractor):
_MAX_RESULTS = 50
IE_NAME = u'youtube:playlist'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
@classmethod
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
- def report_download_page(self, playlist_id, pagenum):
- """Report attempt to download playlist page with given number."""
- self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
-
def _real_extract(self, url):
# Extract playlist id
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
- self._downloader.report_error(u'invalid url: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
# Download playlist videos from API
playlist_id = mobj.group(1) or mobj.group(2)
videos = []
while True:
- self.report_download_page(playlist_id, page_num)
-
url = self._TEMPLATE_URL % (playlist_id, self._MAX_RESULTS, self._MAX_RESULTS * (page_num - 1) + 1)
- try:
- page = compat_urllib_request.urlopen(url).read().decode('utf8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
- return
+ page = self._download_webpage(url, playlist_id, u'Downloading page #%s' % page_num)
try:
response = json.loads(page)
except ValueError as err:
- self._downloader.report_error(u'Invalid JSON in API response: ' + compat_str(err))
- return
+ raise ExtractorError(u'Invalid JSON in API response: ' + compat_str(err))
if 'feed' not in response:
- self._downloader.report_error(u'Got a malformed response from YouTube API')
- return
+ raise ExtractorError(u'Got a malformed response from YouTube API')
+ playlist_title = response['feed']['title']['$t']
if 'entry' not in response['feed']:
# Number of videos is a multiple of self._MAX_RESULTS
break
- playlist_title = response['feed']['title']['$t']
-
videos += [ (entry['yt$position']['$t'], entry['content']['src'])
for entry in response['feed']['entry']
if 'content' in entry ]
_MORE_PAGES_URL = 'http://www.youtube.com/channel_ajax?action_load_more_videos=1&flow=list&paging=%s&view=0&sort=da&channel_id=%s'
IE_NAME = u'youtube:channel'
- def report_download_page(self, channel_id, pagenum):
- """Report attempt to download channel page with given number."""
- self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum))
-
def extract_videos_from_page(self, page):
ids_in_page = []
for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&?', page):
# Extract channel id
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid url: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
# Download channel page
channel_id = mobj.group(1)
video_ids = []
pagenum = 1
- self.report_download_page(channel_id, pagenum)
url = self._TEMPLATE_URL % (channel_id, pagenum)
- request = compat_urllib_request.Request(url)
- try:
- page = compat_urllib_request.urlopen(request).read().decode('utf8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
- return
+ page = self._download_webpage(url, channel_id,
+ u'Downloading page #%s' % pagenum)
# Extract video identifiers
ids_in_page = self.extract_videos_from_page(page)
while True:
pagenum = pagenum + 1
- self.report_download_page(channel_id, pagenum)
url = self._MORE_PAGES_URL % (pagenum, channel_id)
- request = compat_urllib_request.Request(url)
- try:
- page = compat_urllib_request.urlopen(request).read().decode('utf8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
- return
+ page = self._download_webpage(url, channel_id,
+ u'Downloading page #%s' % pagenum)
page = json.loads(page)
_VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]'
IE_NAME = u'youtube:user'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_page(self, username, start_index):
- """Report attempt to download user page."""
- self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
- (username, start_index, start_index + self._GDATA_PAGE_SIZE))
-
def _real_extract(self, url):
# Extract username
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid url: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
username = mobj.group(1)
while True:
start_index = pagenum * self._GDATA_PAGE_SIZE + 1
- self.report_download_page(username, start_index)
-
- request = compat_urllib_request.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index))
- try:
- page = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
- return
+ gdata_url = self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index)
+ page = self._download_webpage(gdata_url, username,
+ u'Downloading video ids from %d to %d' % (start_index, start_index + self._GDATA_PAGE_SIZE))
# Extract video identifiers
ids_in_page = []
_PAGE_SIZE = 12
IE_NAME = u'blip.tv:user'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_page(self, username, pagenum):
- """Report attempt to download user page."""
- self.to_screen(u'user %s: Downloading video ids from page %d' %
- (username, pagenum))
-
def _real_extract(self, url):
# Extract username
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid url: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
username = mobj.group(1)
page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
- request = compat_urllib_request.Request(url)
-
- try:
- page = compat_urllib_request.urlopen(request).read().decode('utf-8')
- mobj = re.search(r'data-users-id="([^"]+)"', page)
- page_base = page_base % mobj.group(1)
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
- return
+ page = self._download_webpage(url, username, u'Downloading user page')
+ mobj = re.search(r'data-users-id="([^"]+)"', page)
+ page_base = page_base % mobj.group(1)
# Download video ids using BlipTV Ajax calls. Result size per
pagenum = 1
while True:
- self.report_download_page(username, pagenum)
url = page_base + "&page=" + str(pagenum)
- request = compat_urllib_request.Request( url )
- try:
- page = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: %s' % str(err))
- return
+ page = self._download_webpage(url, username,
+ u'Downloading video ids from page %d' % pagenum)
# Extract video identifiers
ids_in_page = []
self.report_download_webpage(file_id)
webpage = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'Unable to retrieve file webpage: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to retrieve file webpage: %s' % compat_str(err))
# Search for the real file URL
mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage)
mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL)
if (mobj is not None) and (mobj.group(1) is not None):
restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip()
- self._downloader.report_error(u'%s' % restriction_message)
+ raise ExtractorError(u'%s' % restriction_message)
else:
- self._downloader.report_error(u'unable to extract download URL from: %s' % url)
- return
+ raise ExtractorError(u'Unable to extract download URL from: %s' % url)
file_url = mobj.group(1)
file_extension = os.path.splitext(file_url)[1][1:]
# Search for file title
- mobj = re.search(r'<b title="(.*?)">', webpage)
- if mobj is None:
- self._downloader.report_error(u'unable to extract title')
- return
- file_title = mobj.group(1).decode('utf-8')
+ file_title = self._search_regex(r'<b title="(.*?)">', webpage, u'title')
return [{
'id': file_id.decode('utf-8'),
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('ID')
url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
video_duration = int(video_data['video_duration'])
thumbnail = video_data['thumbnail_src']
- m = re.search('<h2 class="uiHeaderTitle">([^<]+)</h2>', webpage)
- if not m:
- raise ExtractorError(u'Cannot find title in webpage')
- video_title = unescapeHTML(m.group(1))
+ video_title = self._html_search_regex('<h2 class="uiHeaderTitle">([^<]+)</h2>',
+ webpage, u'title')
info = {
'id': video_id,
class BlipTVIE(InfoExtractor):
"""Information extractor for blip.tv"""
- _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$'
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(.+)$'
_URL_EXT = r'^.*\.([a-z0-9]+)$'
IE_NAME = u'blip.tv'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
+ # See https://github.com/rg3/youtube-dl/issues/857
+ api_mobj = re.match(r'http://a\.blip\.tv/api\.swf#(?P<video_id>[\d\w]+)', url)
+ if api_mobj is not None:
+ url = 'http://blip.tv/play/g_%s' % api_mobj.group('video_id')
urlp = compat_urllib_parse_urlparse(url)
if urlp.path.startswith('/play/'):
request = compat_urllib_request.Request(url)
json_code_bytes = urlh.read()
json_code = json_code_bytes.decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to read video info webpage: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to read video info webpage: %s' % compat_str(err))
try:
json_data = json.loads(json_code)
'user_agent': 'iTunes/10.6.1',
}
except (ValueError,KeyError) as err:
- self._downloader.report_error(u'unable to parse video information: %s' % repr(err))
- return
+ raise ExtractorError(u'Unable to parse video information: %s' % repr(err))
return [info]
_VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
IE_NAME = u'myvideo'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
+ # Original Code from: https://github.com/dersphere/plugin.video.myvideo_de.git
+ # Released into the Public Domain by Tristan Fischer on 2013-05-19
+ # https://github.com/rg3/youtube-dl/pull/842
+ def __rc4crypt(self,data, key):
+ x = 0
+ box = list(range(256))
+ for i in list(range(256)):
+ x = (x + box[i] + compat_ord(key[i % len(key)])) % 256
+ box[i], box[x] = box[x], box[i]
+ x = 0
+ y = 0
+ out = ''
+ for char in data:
+ x = (x + 1) % 256
+ y = (y + box[x]) % 256
+ box[x], box[y] = box[y], box[x]
+ out += chr(compat_ord(char) ^ box[(box[x] + box[y]) % 256])
+ return out
+
+ def __md5(self,s):
+ return hashlib.md5(s).hexdigest().encode()
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._download.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'invalid URL: %s' % url)
video_id = mobj.group(1)
+ GK = (
+ b'WXpnME1EZGhNRGhpTTJNM01XVmhOREU0WldNNVpHTTJOakpt'
+ b'TW1FMU5tVTBNR05pWkRaa05XRXhNVFJoWVRVd1ptSXhaVEV3'
+ b'TnpsbA0KTVRkbU1tSTRNdz09'
+ )
+
# Get video webpage
webpage_url = 'http://www.myvideo.de/watch/%s' % video_id
webpage = self._download_webpage(webpage_url, video_id)
- self.report_extraction(video_id)
- mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/.*?\.jpg\'',
- webpage)
- if mobj is None:
- self._downloader.report_error(u'unable to extract media URL')
- return
- video_url = mobj.group(1) + ('/%s.flv' % video_id)
+ mobj = re.search('source src=\'(.+?)[.]([^.]+)\'', webpage)
+ if mobj is not None:
+ self.report_extraction(video_id)
+ video_url = mobj.group(1) + '.flv'
+
+ video_title = self._html_search_regex('<title>([^<]+)</title>',
+ webpage, u'title')
+
+ video_ext = self._search_regex('[.](.+?)$', video_url, u'extension')
+
+ return [{
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': None,
+ 'upload_date': None,
+ 'title': video_title,
+ 'ext': u'flv',
+ }]
- mobj = re.search('<title>([^<]+)</title>', webpage)
+ # try encxml
+ mobj = re.search('var flashvars={(.+?)}', webpage)
if mobj is None:
- self._downloader.report_error(u'unable to extract title')
- return
+ raise ExtractorError(u'Unable to extract video')
+
+ params = {}
+ encxml = ''
+ sec = mobj.group(1)
+ for (a, b) in re.findall('(.+?):\'(.+?)\',?', sec):
+ if not a == '_encxml':
+ params[a] = b
+ else:
+ encxml = compat_urllib_parse.unquote(b)
+ if not params.get('domain'):
+ params['domain'] = 'www.myvideo.de'
+ xmldata_url = '%s?%s' % (encxml, compat_urllib_parse.urlencode(params))
+ if 'flash_playertype=MTV' in xmldata_url:
+ self._downloader.report_warning(u'avoiding MTV player')
+ xmldata_url = (
+ 'http://www.myvideo.de/dynamic/get_player_video_xml.php'
+ '?flash_playertype=D&ID=%s&_countlimit=4&autorun=yes'
+ ) % video_id
+
+ # get enc data
+ enc_data = self._download_webpage(xmldata_url, video_id).split('=')[1]
+ enc_data_b = binascii.unhexlify(enc_data)
+ sk = self.__md5(
+ base64.b64decode(base64.b64decode(GK)) +
+ self.__md5(
+ str(video_id).encode('utf-8')
+ )
+ )
+ dec_data = self.__rc4crypt(enc_data_b, sk)
- video_title = mobj.group(1)
+ # extracting infos
+ self.report_extraction(video_id)
+
+ video_url = None
+ mobj = re.search('connectionurl=\'(.*?)\'', dec_data)
+ if mobj:
+ video_url = compat_urllib_parse.unquote(mobj.group(1))
+ if 'myvideo2flash' in video_url:
+ self._downloader.report_warning(u'forcing RTMPT ...')
+ video_url = video_url.replace('rtmpe://', 'rtmpt://')
+
+ if not video_url:
+ # extract non rtmp videos
+ mobj = re.search('path=\'(http.*?)\' source=\'(.*?)\'', dec_data)
+ if mobj is None:
+ raise ExtractorError(u'unable to extract url')
+ video_url = compat_urllib_parse.unquote(mobj.group(1)) + compat_urllib_parse.unquote(mobj.group(2))
+
+ video_file = self._search_regex('source=\'(.*?)\'', dec_data, u'video file')
+ video_file = compat_urllib_parse.unquote(video_file)
+
+ if not video_file.endswith('f4m'):
+ ppath, prefix = video_file.split('.')
+ video_playpath = '%s:%s' % (prefix, ppath)
+ video_hls_playlist = ''
+ else:
+ video_playpath = ''
+ video_hls_playlist = (
+ video_filepath + video_file
+ ).replace('.f4m', '.m3u8')
+
+ video_swfobj = self._search_regex('swfobject.embedSWF\(\'(.+?)\'', webpage, u'swfobj')
+ video_swfobj = compat_urllib_parse.unquote(video_swfobj)
+
+ video_title = self._html_search_regex("<h1(?: class='globalHd')?>(.*?)</h1>",
+ webpage, u'title')
return [{
- 'id': video_id,
- 'url': video_url,
- 'uploader': None,
- 'upload_date': None,
- 'title': video_title,
- 'ext': u'flv',
+ 'id': video_id,
+ 'url': video_url,
+ 'tc_url': video_url,
+ 'uploader': None,
+ 'upload_date': None,
+ 'title': video_title,
+ 'ext': u'flv',
+ 'play_path': video_playpath,
+ 'video_file': video_file,
+ 'video_hls_playlist': video_hls_playlist,
+ 'player_url': video_swfobj,
}]
+
class ComedyCentralIE(InfoExtractor):
"""Information extractor for The Daily Show and Colbert Report """
"""Receives a URL and returns True if suitable for this IE."""
return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
- def report_config_download(self, episode_id, media_id):
- self.to_screen(u'%s: Downloading configuration for %s' % (episode_id, media_id))
-
- def report_index_download(self, episode_id):
- self.to_screen(u'%s: Downloading show index' % episode_id)
-
def _print_formats(self, formats):
print('Available formats:')
for x in formats:
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
if mobj.group('shortname'):
if mobj.group('shortname') in ('tds', 'thedailyshow'):
else:
epTitle = mobj.group('episode')
- req = compat_urllib_request.Request(url)
self.report_extraction(epTitle)
- try:
- htmlHandle = compat_urllib_request.urlopen(req)
- html = htmlHandle.read()
- webpage = html.decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
- return
+ webpage,htmlHandle = self._download_webpage_handle(url, epTitle)
if dlNewest:
url = htmlHandle.geturl()
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
- self._downloader.report_error(u'Invalid redirected URL: ' + url)
- return
+ raise ExtractorError(u'Invalid redirected URL: ' + url)
if mobj.group('episode') == '':
- self._downloader.report_error(u'Redirected URL is still not specific: ' + url)
- return
+ raise ExtractorError(u'Redirected URL is still not specific: ' + url)
epTitle = mobj.group('episode')
mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
if len(altMovieParams) == 0:
- self._downloader.report_error(u'unable to find Flash URL in webpage ' + url)
- return
+ raise ExtractorError(u'unable to find Flash URL in webpage ' + url)
else:
mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
uri = mMovieParams[0][1]
indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
- self.report_index_download(epTitle)
- try:
- indexXml = compat_urllib_request.urlopen(indexUrl).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download episode index: ' + compat_str(err))
- return
+ indexXml = self._download_webpage(indexUrl, epTitle,
+ u'Downloading show index',
+ u'unable to download episode index')
results = []
shortMediaId = mediaId.split(':')[-1]
showId = mediaId.split(':')[-2].replace('.com', '')
officialTitle = itemEl.findall('./title')[0].text
- officialDate = itemEl.findall('./pubDate')[0].text
+ officialDate = unified_strdate(itemEl.findall('./pubDate')[0].text)
configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
compat_urllib_parse.urlencode({'uri': mediaId}))
- configReq = compat_urllib_request.Request(configUrl)
- self.report_config_download(epTitle, shortMediaId)
- try:
- configXml = compat_urllib_request.urlopen(configReq).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: %s' % compat_str(err))
- return
+ configXml = self._download_webpage(configUrl, epTitle,
+ u'Downloading configuration for %s' % shortMediaId)
cdoc = xml.etree.ElementTree.fromstring(configXml)
turls = []
_VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
IE_NAME = u'escapist'
- def report_config_download(self, showName):
- self.to_screen(u'%s: Downloading configuration' % showName)
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
showName = mobj.group('showname')
videoId = mobj.group('episode')
- self.report_extraction(showName)
- try:
- webPage = compat_urllib_request.urlopen(url)
- webPageBytes = webPage.read()
- m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type'])
- webPage = webPageBytes.decode(m.group(1) if m else 'utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download webpage: ' + compat_str(err))
- return
+ self.report_extraction(videoId)
+ webpage = self._download_webpage(url, videoId)
- descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
- description = unescapeHTML(descMatch.group(1))
- imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage)
- imgUrl = unescapeHTML(imgMatch.group(1))
- playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage)
- playerUrl = unescapeHTML(playerUrlMatch.group(1))
- configUrlMatch = re.search('config=(.*)$', playerUrl)
- configUrl = compat_urllib_parse.unquote(configUrlMatch.group(1))
+ videoDesc = self._html_search_regex('<meta name="description" content="([^"]*)"',
+ webpage, u'description', fatal=False)
- self.report_config_download(showName)
- try:
- configJSON = compat_urllib_request.urlopen(configUrl)
- m = re.match(r'text/html; charset="?([^"]+)"?', configJSON.headers['Content-Type'])
- configJSON = configJSON.read().decode(m.group(1) if m else 'utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download configuration: ' + compat_str(err))
- return
+ imgUrl = self._html_search_regex('<meta property="og:image" content="([^"]*)"',
+ webpage, u'thumbnail', fatal=False)
+
+ playerUrl = self._html_search_regex('<meta property="og:video" content="([^"]*)"',
+ webpage, u'player url')
+
+ title = self._html_search_regex('<meta name="title" content="([^"]*)"',
+ webpage, u'player url').split(' : ')[-1]
+
+ configUrl = self._search_regex('config=(.*)$', playerUrl, u'config url')
+ configUrl = compat_urllib_parse.unquote(configUrl)
+
+ configJSON = self._download_webpage(configUrl, videoId,
+ u'Downloading configuration',
+ u'unable to download configuration')
# Technically, it's JavaScript, not JSON
configJSON = configJSON.replace("'", '"')
try:
config = json.loads(configJSON)
except (ValueError,) as err:
- self._downloader.report_error(u'Invalid JSON in configuration file: ' + compat_str(err))
- return
+ raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
playlist = config['playlist']
videoUrl = playlist[1]['url']
'url': videoUrl,
'uploader': showName,
'upload_date': None,
- 'title': showName,
+ 'title': title,
'ext': 'mp4',
'thumbnail': imgUrl,
- 'description': description,
+ 'description': videoDesc,
'player_url': playerUrl,
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('videoid')
info = {
try:
metaXml = compat_urllib_request.urlopen(xmlUrl).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download video info XML: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
mdoc = xml.etree.ElementTree.fromstring(metaXml)
try:
info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
manifest_url = videoNode.findall('./file')[0].text
except IndexError:
- self._downloader.report_error(u'Invalid metadata XML file')
- return
+ raise ExtractorError(u'Invalid metadata XML file')
manifest_url += '?hdcore=2.10.3'
self.report_manifest(video_id)
try:
manifestXml = compat_urllib_request.urlopen(manifest_url).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download video info XML: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
adoc = xml.etree.ElementTree.fromstring(manifestXml)
try:
node_id = media_node.attrib['url']
video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
except IndexError as err:
- self._downloader.report_error(u'Invalid manifest file')
- return
+ raise ExtractorError(u'Invalid manifest file')
url_pr = compat_urllib_parse_urlparse(manifest_url)
url = url_pr.scheme + '://' + url_pr.netloc + '/z' + video_id[:-2] + '/' + node_id + 'Seg1-Frag1'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(1)
webpage = self._download_webpage(url, video_id)
self.report_extraction(video_id)
-
# Extract video URL
- mobj = re.search(r'flv_url=(.+?)&', webpage)
- if mobj is None:
- self._downloader.report_error(u'unable to extract video url')
- return
- video_url = compat_urllib_parse.unquote(mobj.group(1))
-
+ video_url = compat_urllib_parse.unquote(self._search_regex(r'flv_url=(.+?)&',
+ webpage, u'video URL'))
# Extract title
- mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage)
- if mobj is None:
- self._downloader.report_error(u'unable to extract video title')
- return
- video_title = mobj.group(1)
-
+ video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XVID',
+ webpage, u'title')
# Extract video thumbnail
- mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)', webpage)
- if mobj is None:
- self._downloader.report_error(u'unable to extract video thumbnail')
- return
- video_thumbnail = mobj.group(0)
+ video_thumbnail = self._search_regex(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)',
+ webpage, u'thumbnail', fatal=False)
info = {
'id': video_id,
_VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)'
IE_NAME = u'soundcloud'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
def report_resolve(self, video_id):
"""Report information extraction."""
self.to_screen(u'%s: Resolving id' % video_id)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
# extract uploader (which is in the url)
uploader = mobj.group(1)
# extract simple title (uploader + slug of song title)
slug_title = mobj.group(2)
simple_title = uploader + u'-' + slug_title
+ full_title = '%s/%s' % (uploader, slug_title)
- self.report_resolve('%s/%s' % (uploader, slug_title))
+ self.report_resolve(full_title)
url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title)
resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
- request = compat_urllib_request.Request(resolv_url)
- try:
- info_json_bytes = compat_urllib_request.urlopen(request).read()
- info_json = info_json_bytes.decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err))
- return
+ info_json = self._download_webpage(resolv_url, full_title, u'Downloading info JSON')
info = json.loads(info_json)
video_id = info['id']
- self.report_extraction('%s/%s' % (uploader, slug_title))
+ self.report_extraction(full_title)
streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
- request = compat_urllib_request.Request(streams_url)
- try:
- stream_json_bytes = compat_urllib_request.urlopen(request).read()
- stream_json = stream_json_bytes.decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download stream definitions: %s' % compat_str(err))
- return
+ stream_json = self._download_webpage(streams_url, full_title,
+ u'Downloading stream definitions',
+ u'unable to download stream definitions')
streams = json.loads(stream_json)
mediaURL = streams['http_mp3_128_url']
+ upload_date = unified_strdate(info['created_at'])
return [{
'id': info['id'],
'url': mediaURL,
'uploader': info['user']['username'],
- 'upload_date': info['created_at'],
+ 'upload_date': upload_date,
'title': info['title'],
'ext': u'mp3',
'description': info['description'],
"""
_VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)'
- IE_NAME = u'soundcloud'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
+ IE_NAME = u'soundcloud:set'
def report_resolve(self, video_id):
"""Report information extraction."""
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
# extract uploader (which is in the url)
uploader = mobj.group(1)
# extract simple title (uploader + slug of song title)
slug_title = mobj.group(2)
simple_title = uploader + u'-' + slug_title
+ full_title = '%s/sets/%s' % (uploader, slug_title)
- self.report_resolve('%s/sets/%s' % (uploader, slug_title))
+ self.report_resolve(full_title)
url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title)
resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
- request = compat_urllib_request.Request(resolv_url)
- try:
- info_json_bytes = compat_urllib_request.urlopen(request).read()
- info_json = info_json_bytes.decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err))
- return
+ info_json = self._download_webpage(resolv_url, full_title)
videos = []
info = json.loads(info_json)
self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err['error_message']))
return
+ self.report_extraction(full_title)
for track in info['tracks']:
video_id = track['id']
- self.report_extraction('%s/sets/%s' % (uploader, slug_title))
streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
- request = compat_urllib_request.Request(streams_url)
- try:
- stream_json_bytes = compat_urllib_request.urlopen(request).read()
- stream_json = stream_json_bytes.decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download stream definitions: %s' % compat_str(err))
- return
+ stream_json = self._download_webpage(streams_url, video_id, u'Downloading track info JSON')
+ self.report_extraction(video_id)
streams = json.loads(stream_json)
mediaURL = streams['http_mp3_128_url']
'id': video_id,
'url': mediaURL,
'uploader': track['user']['username'],
- 'upload_date': track['created_at'],
+ 'upload_date': unified_strdate(track['created_at']),
'title': track['title'],
'ext': u'mp3',
'description': track['description'],
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
webpage = self._download_webpage(url, video_id=url)
self.report_extraction(url)
# Extract video URL
mobj = re.search(r"jsclassref ?= ?'([^']*)'", webpage)
if mobj is None:
- self._downloader.report_error(u'unable to extract video url')
- return
+ raise ExtractorError(u'Unable to extract video url')
real_id = compat_urllib_parse.unquote(base64.b64decode(mobj.group(1).encode('ascii')).decode('utf-8'))
video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
# Extract title
- mobj = re.search(r'contentTitle = "(.*?)";', webpage)
- if mobj is None:
- self._downloader.report_error(u'unable to extract video title')
- return
- video_title = mobj.group(1)
+ video_title = self._search_regex(r'contentTitle = "(.*?)";',
+ webpage, u'title')
# Extract description
- video_description = u'No description available.'
- mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage)
- if mobj is not None:
- video_description = mobj.group(1)
+ video_description = self._html_search_regex(r'<meta name="description" content="(.*)"(?:\s*/)?>',
+ webpage, u'description', fatal=False)
video_filename = video_url.split('/')[-1]
video_id, extension = video_filename.split('.')
_VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
IE_NAME = u'mixcloud'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
def report_download_json(self, file_id):
"""Report JSON download."""
self.to_screen(u'Downloading json')
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
# extract uploader & filename from url
uploader = mobj.group(1).decode('utf-8')
file_id = uploader + "-" + mobj.group(2).decode('utf-8')
self.report_download_json(file_url)
jsonData = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'Unable to retrieve file: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to retrieve file: %s' % compat_str(err))
# parse JSON
json_data = json.loads(jsonData)
break # got it!
else:
if req_format not in formats:
- self._downloader.report_error(u'format is not available')
- return
+ raise ExtractorError(u'Format is not available')
url_list = self.get_urls(formats, req_format)
file_url = self.check_urls(url_list)
try:
metaXml = compat_urllib_request.urlopen(xmlUrl).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download video info XML: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
mdoc = xml.etree.ElementTree.fromstring(metaXml)
try:
info['title'] = mdoc.findall('./title')[0].text
info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
except IndexError:
- self._downloader.report_error(u'Invalid metadata XML file')
- return
+ raise ExtractorError(u'Invalid metadata XML file')
info['ext'] = info['url'].rpartition('.')[2]
return [info]
elif mobj.group('course'): # A course page
note='Downloading course info page',
errnote='Unable to download course info page')
- m = re.search('<h1>([^<]+)</h1>', coursepage)
- if m:
- info['title'] = unescapeHTML(m.group(1))
- else:
- info['title'] = info['id']
+ info['title'] = self._html_search_regex('<h1>([^<]+)</h1>', coursepage, 'title', default=info['id'])
- m = re.search('<description>([^<]+)</description>', coursepage)
- if m:
- info['description'] = unescapeHTML(m.group(1))
+ info['description'] = self._html_search_regex('<description>([^<]+)</description>',
+ coursepage, u'description', fatal=False)
links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage))
info['list'] = [
try:
rootpage = compat_urllib_request.urlopen(rootURL).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download course info page: ' + compat_str(err))
- return
+ raise ExtractorError(u'Unable to download course info page: ' + compat_str(err))
info['title'] = info['id']
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
if not mobj.group('proto'):
url = 'http://' + url
video_id = mobj.group('videoid')
webpage = self._download_webpage(url, video_id)
- mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage)
- if mobj is None:
- self._downloader.report_error(u'unable to extract song name')
- return
- song_name = unescapeHTML(mobj.group(1).decode('iso-8859-1'))
- mobj = re.search(r'<meta name="mtv_an" content="([^"]+)"/>', webpage)
- if mobj is None:
- self._downloader.report_error(u'unable to extract performer')
- return
- performer = unescapeHTML(mobj.group(1).decode('iso-8859-1'))
- video_title = performer + ' - ' + song_name
+ song_name = self._html_search_regex(r'<meta name="mtv_vt" content="([^"]+)"/>',
+ webpage, u'song name', fatal=False)
- mobj = re.search(r'<meta name="mtvn_uri" content="([^"]+)"/>', webpage)
- if mobj is None:
- self._downloader.report_error(u'unable to mtvn_uri')
- return
- mtvn_uri = mobj.group(1)
+ video_title = self._html_search_regex(r'<meta name="mtv_an" content="([^"]+)"/>',
+ webpage, u'title')
- mobj = re.search(r'MTVN.Player.defaultPlaylistId = ([0-9]+);', webpage)
- if mobj is None:
- self._downloader.report_error(u'unable to extract content id')
- return
- content_id = mobj.group(1)
+ mtvn_uri = self._html_search_regex(r'<meta name="mtvn_uri" content="([^"]+)"/>',
+ webpage, u'mtvn_uri', fatal=False)
+
+ content_id = self._search_regex(r'MTVN.Player.defaultPlaylistId = ([0-9]+);',
+ webpage, u'content id', fatal=False)
videogen_url = 'http://www.mtv.com/player/includes/mediaGen.jhtml?uri=' + mtvn_uri + '&id=' + content_id + '&vid=' + video_id + '&ref=www.mtvn.com&viewUri=' + mtvn_uri
self.report_extraction(video_id)
try:
metadataXml = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download video metadata: %s' % compat_str(err))
- return
+ raise ExtractorError(u'Unable to download video metadata: %s' % compat_str(err))
mdoc = xml.etree.ElementTree.fromstring(metadataXml)
renditions = mdoc.findall('.//rendition')
format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
video_url = rendition.find('./src').text
except KeyError:
- self._downloader.report_error('Invalid rendition field.')
- return
+ raise ExtractorError('Invalid rendition field.')
info = {
'id': video_id,
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('ID')
info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id
- request = compat_urllib_request.Request(info_url, None, std_headers)
- try:
- self.report_download_webpage(video_id)
- jsondata = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err))
- return
+ jsondata = self._download_webpage(info_url, video_id)
self.report_extraction(video_id)
try:
- jsonstr = jsondata.decode('utf-8')
- config = json.loads(jsonstr)
+ config = json.loads(jsondata)
video_title = config['data'][0]['title']
seed = config['data'][0]['seed']
fileid = config['data'][0]['streamfileids'][format]
keys = [s['k'] for s in config['data'][0]['segs'][format]]
except (UnicodeDecodeError, ValueError, KeyError):
- self._downloader.report_error(u'unable to extract info section')
- return
+ raise ExtractorError(u'Unable to extract info section')
files_info=[]
sid = self._gen_sid()
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(1)
- self.report_download_webpage(video_id)
-
# Get webpage content
- try:
- webpage_bytes = compat_urllib_request.urlopen(url).read()
- webpage = webpage_bytes.decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download video webpage: %s' % err)
- return
+ webpage = self._download_webpage(url, video_id)
- result = re.search(self.VIDEO_URL_RE, webpage)
- if result is None:
- self._downloader.report_error(u'unable to extract video url')
- return
- video_url = compat_urllib_parse.unquote(result.group(1))
+ video_url = self._search_regex(self.VIDEO_URL_RE,
+ webpage, u'video URL')
+ video_url = compat_urllib_parse.unquote(video_url)
- result = re.search(self.VIDEO_TITLE_RE, webpage)
- if result is None:
- self._downloader.report_error(u'unable to extract video title')
- return
- video_title = result.group(1)
+ video_title = self._html_search_regex(self.VIDEO_TITLE_RE,
+ webpage, u'title')
- result = re.search(self.VIDEO_THUMB_RE, webpage)
- if result is None:
- self._downloader.report_error(u'unable to extract video thumbnail')
- return
- video_thumbnail = result.group(1)
+ video_thumbnail = self._search_regex(self.VIDEO_THUMB_RE,
+ webpage, u'thumbnail', fatal=False)
return [{
'id': video_id,
_VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)'
IE_NAME = u'plus.google'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_extract_entry(self, url):
- """Report downloading extry"""
- self.to_screen(u'Downloading entry: %s' % url)
-
- def report_date(self, upload_date):
- """Report downloading extry"""
- self.to_screen(u'Entry date: %s' % upload_date)
-
- def report_uploader(self, uploader):
- """Report downloading extry"""
- self.to_screen(u'Uploader: %s' % uploader)
-
- def report_title(self, video_title):
- """Report downloading extry"""
- self.to_screen(u'Title: %s' % video_title)
-
- def report_extract_vid_page(self, video_page):
- """Report information extraction."""
- self.to_screen(u'Extracting video page: %s' % video_page)
-
def _real_extract(self, url):
# Extract id from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'Invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
post_url = mobj.group(0)
video_id = mobj.group(1)
video_extension = 'flv'
# Step 1, Retrieve post webpage to extract further information
- self.report_extract_entry(post_url)
- request = compat_urllib_request.Request(post_url)
- try:
- webpage = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'Unable to retrieve entry webpage: %s' % compat_str(err))
- return
+ webpage = self._download_webpage(post_url, video_id, u'Downloading entry webpage')
+
+ self.report_extraction(video_id)
# Extract update date
- upload_date = None
- pattern = 'title="Timestamp">(.*?)</a>'
- mobj = re.search(pattern, webpage)
- if mobj:
- upload_date = mobj.group(1)
+ upload_date = self._html_search_regex('title="Timestamp">(.*?)</a>',
+ webpage, u'upload date', fatal=False)
+ if upload_date:
# Convert timestring to a format suitable for filename
upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d")
upload_date = upload_date.strftime('%Y%m%d')
- self.report_date(upload_date)
# Extract uploader
- uploader = None
- pattern = r'rel\="author".*?>(.*?)</a>'
- mobj = re.search(pattern, webpage)
- if mobj:
- uploader = mobj.group(1)
- self.report_uploader(uploader)
+ uploader = self._html_search_regex(r'rel\="author".*?>(.*?)</a>',
+ webpage, u'uploader', fatal=False)
# Extract title
# Get the first line for title
- video_title = u'NA'
- pattern = r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]'
- mobj = re.search(pattern, webpage)
- if mobj:
- video_title = mobj.group(1)
- self.report_title(video_title)
+ video_title = self._html_search_regex(r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]',
+ webpage, 'title', default=u'NA')
# Step 2, Stimulate clicking the image box to launch video
- pattern = '"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]'
- mobj = re.search(pattern, webpage)
- if mobj is None:
- self._downloader.report_error(u'unable to extract video page URL')
-
- video_page = mobj.group(1)
- request = compat_urllib_request.Request(video_page)
- try:
- webpage = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'Unable to retrieve video webpage: %s' % compat_str(err))
- return
- self.report_extract_vid_page(video_page)
-
+ video_page = self._search_regex('"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]',
+ webpage, u'video page URL')
+ webpage = self._download_webpage(video_page, video_id, u'Downloading video page')
# Extract video links on video page
"""Extract video links of all sizes"""
pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
mobj = re.findall(pattern, webpage)
if len(mobj) == 0:
- self._downloader.report_error(u'unable to extract video links')
+ raise ExtractorError(u'Unable to extract video links')
# Sort in resolution
links = sorted(mobj)
}]
class NBAIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*)(\?.*)?$'
+ _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
IE_NAME = u'nba'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(1)
- if video_id.endswith('/index.html'):
- video_id = video_id[:-len('/index.html')]
webpage = self._download_webpage(url, video_id)
video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
- def _findProp(rexp, default=None):
- m = re.search(rexp, webpage)
- if m:
- return unescapeHTML(m.group(1))
- else:
- return default
shortened_video_id = video_id.rpartition('/')[2]
- title = _findProp(r'<meta property="og:title" content="(.*?)"', shortened_video_id).replace('NBA.com: ', '')
+ title = self._html_search_regex(r'<meta property="og:title" content="(.*?)"',
+ webpage, 'title', default=shortened_video_id).replace('NBA.com: ', '')
+
+ # It isn't there in the HTML it returns to us
+ # uploader_date = self._html_search_regex(r'<b>Date:</b> (.*?)</div>', webpage, 'upload_date', fatal=False)
+
+ description = self._html_search_regex(r'<meta name="description" (?:content|value)="(.*?)" />', webpage, 'description', fatal=False)
+
info = {
'id': shortened_video_id,
'url': video_url,
'ext': 'mp4',
'title': title,
- 'uploader_date': _findProp(r'<b>Date:</b> (.*?)</div>'),
- 'description': _findProp(r'<div class="description">(.*?)</h1>'),
+ # 'uploader_date': uploader_date,
+ 'description': description,
}
return [info]
# starts at 1 and increases. Can we treat all parts as one video?
_VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?(?:twitch|justin)\.tv/
- ([^/]+)(?:/b/([^/]+))?/?(?:\#.*)?$"""
+ (?:
+ (?P<channelid>[^/]+)|
+ (?:(?:[^/]+)/b/(?P<videoid>[^/]+))|
+ (?:(?:[^/]+)/c/(?P<chapterid>[^/]+))
+ )
+ /?(?:\#.*)?$
+ """
_JUSTIN_PAGE_LIMIT = 100
IE_NAME = u'justin.tv'
(channel, offset, offset + self._JUSTIN_PAGE_LIMIT))
# Return count of items, list of *valid* items
- def _parse_page(self, url):
- try:
- urlh = compat_urllib_request.urlopen(url)
- webpage_bytes = urlh.read()
- webpage = webpage_bytes.decode('utf-8', 'ignore')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_error(u'unable to download video info JSON: %s' % compat_str(err))
- return
+ def _parse_page(self, url, video_id):
+ webpage = self._download_webpage(url, video_id,
+ u'Downloading video info JSON',
+ u'unable to download video info JSON')
response = json.loads(webpage)
if type(response) != list:
error_text = response.get('error', 'unknown error')
- self._downloader.report_error(u'Justin.tv API: %s' % error_text)
- return
+ raise ExtractorError(u'Justin.tv API: %s' % error_text)
info = []
for clip in response:
video_url = clip['video_file_url']
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'invalid URL: %s' % url)
- api = 'http://api.justin.tv'
- video_id = mobj.group(mobj.lastindex)
+ api_base = 'http://api.justin.tv'
paged = False
- if mobj.lastindex == 1:
+ if mobj.group('channelid'):
paged = True
- api += '/channel/archives/%s.json'
+ video_id = mobj.group('channelid')
+ api = api_base + '/channel/archives/%s.json' % video_id
+ elif mobj.group('chapterid'):
+ chapter_id = mobj.group('chapterid')
+
+ webpage = self._download_webpage(url, chapter_id)
+ m = re.search(r'PP\.archive_id = "([0-9]+)";', webpage)
+ if not m:
+ raise ExtractorError(u'Cannot find archive of a chapter')
+ archive_id = m.group(1)
+
+ api = api_base + '/broadcast/by_chapter/%s.xml' % chapter_id
+ chapter_info_xml = self._download_webpage(api, chapter_id,
+ note=u'Downloading chapter information',
+ errnote=u'Chapter information download failed')
+ doc = xml.etree.ElementTree.fromstring(chapter_info_xml)
+ for a in doc.findall('.//archive'):
+ if archive_id == a.find('./id').text:
+ break
+ else:
+ raise ExtractorError(u'Could not find chapter in chapter information')
+
+ video_url = a.find('./video_file_url').text
+ video_ext = video_url.rpartition('.')[2] or u'flv'
+
+ chapter_api_url = u'https://api.twitch.tv/kraken/videos/c' + chapter_id
+ chapter_info_json = self._download_webpage(chapter_api_url, u'c' + chapter_id,
+ note='Downloading chapter metadata',
+ errnote='Download of chapter metadata failed')
+ chapter_info = json.loads(chapter_info_json)
+
+ bracket_start = int(doc.find('.//bracket_start').text)
+ bracket_end = int(doc.find('.//bracket_end').text)
+
+ # TODO determine start (and probably fix up file)
+ # youtube-dl -v http://www.twitch.tv/firmbelief/c/1757457
+ #video_url += u'?start=' + TODO:start_timestamp
+ # bracket_start is 13290, but we want 51670615
+ self._downloader.report_warning(u'Chapter detected, but we can just download the whole file. '
+ u'Chapter starts at %s and ends at %s' % (formatSeconds(bracket_start), formatSeconds(bracket_end)))
+
+ info = {
+ 'id': u'c' + chapter_id,
+ 'url': video_url,
+ 'ext': video_ext,
+ 'title': chapter_info['title'],
+ 'thumbnail': chapter_info['preview'],
+ 'description': chapter_info['description'],
+ 'uploader': chapter_info['channel']['display_name'],
+ 'uploader_id': chapter_info['channel']['name'],
+ }
+ return [info]
else:
- api += '/broadcast/by_archive/%s.json'
- api = api % (video_id,)
+ video_id = mobj.group('videoid')
+ api = api_base + '/broadcast/by_archive/%s.json' % video_id
self.report_extraction(video_id)
if paged:
self.report_download_page(video_id, offset)
page_url = api + ('?offset=%d&limit=%d' % (offset, limit))
- page_count, page_info = self._parse_page(page_url)
+ page_count, page_info = self._parse_page(page_url, video_id)
info.extend(page_info)
if not paged or page_count != limit:
break
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'invalid URL: %s' % url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
- m = re.search(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"', webpage, re.DOTALL)
- if not m:
- self._downloader.report_error(u'unable to find video information')
- video_url = unescapeHTML(m.group('url'))
+ video_url = self._html_search_regex(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"',
+ webpage, u'video URL', flags=re.DOTALL)
- m = re.search(r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>", webpage, flags=re.DOTALL)
- if not m:
- m = re.search(r'<title>(?P<title>[^<]+?)</title>', webpage)
- if not m:
- self._downloader.report_error(u'Cannot find video title')
- title = clean_html(m.group('title'))
+ title = self._html_search_regex((r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>",
+ r'<title>(?P<title>[^<]+?)</title>'), webpage, 'title', flags=re.DOTALL)
- m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
- if m:
- desc = unescapeHTML(m.group('desc'))
- else:
- desc = None
+ video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
+ webpage, u'description', fatal=False, flags=re.DOTALL)
info = {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': title,
- 'description': desc,
+ 'description': video_description,
}
return [info]
class SteamIE(InfoExtractor):
- _VALID_URL = r"""http://store.steampowered.com/
+ _VALID_URL = r"""http://store\.steampowered\.com/
+ (agecheck/)?
(?P<urltype>video|app)/ #If the page is only for videos or for a game
(?P<gameID>\d+)/?
(?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID
video_url = vid.group('videoURL')
video_thumb = thumb.group('thumbnail')
if not video_url:
- self._downloader.report_error(u'Cannot find video url for %s' % video_id)
+ raise ExtractorError(u'Cannot find video url for %s' % video_id)
info = {
'id':video_id,
'url':video_url,
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('videoID')
+
video_url = u'http://tcdn.ustream.tv/video/%s' % video_id
webpage = self._download_webpage(url, video_id)
- m = re.search(r'data-title="(?P<title>.+)"',webpage)
- title = m.group('title')
- m = re.search(r'<a class="state" data-content-type="channel" data-content-id="(?P<uploader>\d+)"',webpage)
- uploader = m.group('uploader')
+
+ self.report_extraction(video_id)
+
+ video_title = self._html_search_regex(r'data-title="(?P<title>.+)"',
+ webpage, u'title')
+
+ uploader = self._html_search_regex(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>',
+ webpage, u'uploader', fatal=False, flags=re.DOTALL)
+
+ thumbnail = self._html_search_regex(r'<link rel="image_src" href="(?P<thumb>.*?)"',
+ webpage, u'thumbnail', fatal=False)
+
info = {
- 'id':video_id,
- 'url':video_url,
+ 'id': video_id,
+ 'url': video_url,
'ext': 'flv',
- 'title': title,
- 'uploader': uploader
- }
- return [info]
+ 'title': video_title,
+ 'uploader': uploader,
+ 'thumbnail': thumbnail,
+ }
+ return info
class WorldStarHipHopIE(InfoExtractor):
- _VALID_URL = r'http://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
+ _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
IE_NAME = u'WorldStarHipHop'
def _real_extract(self, url):
- _src_url = r"""(http://hw-videos.*(?:mp4|flv))"""
-
- webpage_src = compat_urllib_request.urlopen(url).read()
- webpage_src = webpage_src.decode('utf-8')
-
- mobj = re.search(_src_url, webpage_src)
-
m = re.match(self._VALID_URL, url)
video_id = m.group('id')
- if mobj is not None:
- video_url = mobj.group()
- if 'mp4' in video_url:
- ext = 'mp4'
- else:
- ext = 'flv'
- else:
- self._downloader.report_error(u'Cannot find video url for %s' % video_id)
- return
-
- _title = r"""<title>(.*)</title>"""
+ webpage_src = self._download_webpage(url, video_id)
- mobj = re.search(_title, webpage_src)
+ video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)',
+ webpage_src, u'video URL')
- if mobj is not None:
- title = mobj.group(1)
+ if 'mp4' in video_url:
+ ext = 'mp4'
else:
- title = 'World Start Hip Hop - %s' % time.ctime()
+ ext = 'flv'
- _thumbnail = r"""rel="image_src" href="(.*)" />"""
- mobj = re.search(_thumbnail, webpage_src)
+ video_title = self._html_search_regex(r"<title>(.*)</title>",
+ webpage_src, u'title')
# Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
- if mobj is not None:
- thumbnail = mobj.group(1)
- else:
+ thumbnail = self._html_search_regex(r'rel="image_src" href="(.*)" />',
+ webpage_src, u'thumbnail', fatal=False)
+
+ if not thumbnail:
_title = r"""candytitles.*>(.*)</span>"""
mobj = re.search(_title, webpage_src)
if mobj is not None:
- title = mobj.group(1)
- thumbnail = None
+ video_title = mobj.group(1)
results = [{
'id': video_id,
'url' : video_url,
- 'title' : title,
+ 'title' : video_title,
'thumbnail' : thumbnail,
'ext' : ext,
}]
video_id = m.group('videoID')
webpage = self._download_webpage(url, video_id)
- m = re.search(r'<script>window.gon = {.*?};gon\.show=(.+?);</script>', webpage)
- if not m:
- raise ExtractorError(u'Cannot find metadata')
- json_data = m.group(1)
+
+ json_data = self._search_regex(r'<script>window.gon = {.*?};gon\.show=(.+?);</script>',
+ webpage, u'json data')
try:
data = json.loads(json_data)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
-
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('videoid')
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
- # Get the video title
- result = re.search(r'<h1.*?>(?P<title>.*)</h1>', webpage)
- if result is None:
- raise ExtractorError(u'Unable to extract video title')
- video_title = result.group('title').strip()
-
- # Get the video date
- result = re.search(r'Date:</label>(?P<date>.*) </li>', webpage)
- if result is None:
- self._downloader.report_warning(u'unable to extract video date')
- upload_date = None
- else:
- upload_date = result.group('date').strip()
+ # Get JSON parameters
+ json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, u'JSON parameters')
+ try:
+ params = json.loads(json_params)
+ except:
+ raise ExtractorError(u'Invalid JSON')
- # Get the video uploader
- result = re.search(r'Submitted:</label>(?P<uploader>.*)</li>', webpage)
- if result is None:
- self._downloader.report_warning(u'unable to extract uploader')
- video_uploader = None
- else:
- video_uploader = result.group('uploader').strip()
- video_uploader = clean_html( video_uploader )
+ self.report_extraction(video_id)
+ try:
+ video_title = params['title']
+ upload_date = unified_strdate(params['release_date_f'])
+ video_description = params['description']
+ video_uploader = params['submitted_by']
+ thumbnail = params['thumbnails'][0]['image']
+ except KeyError:
+ raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
# Get all of the formats available
DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
- result = re.search(DOWNLOAD_LIST_RE, webpage)
- if result is None:
- raise ExtractorError(u'Unable to extract download list')
- download_list_html = result.group('download_list').strip()
+ download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
+ webpage, u'download list').strip()
# Get all of the links from the page
LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
size = format[0]
bitrate = format[1]
format = "-".join( format )
- title = u'%s-%s-%s' % (video_title, size, bitrate)
+ # title = u'%s-%s-%s' % (video_title, size, bitrate)
formats.append({
'id': video_id,
'url': video_url,
'uploader': video_uploader,
'upload_date': upload_date,
- 'title': title,
+ 'title': video_title,
'ext': extension,
'format': format,
- 'thumbnail': None,
- 'description': None,
- 'player_url': None
+ 'thumbnail': thumbnail,
+ 'description': video_description
})
if self._downloader.params.get('listformats', None):
else:
format = self._specific( req_format, formats )
if result is None:
- self._downloader.report_error(u'requested format not available')
- return
+ raise ExtractorError(u'Requested format not available')
return [format]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('videoid')
video_title = mobj.group('title')
# Get the video URL
VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",'
- result = re.search(VIDEO_URL_RE, webpage)
- if result is None:
- self._downloader.report_error(u'unable to extract video url')
- return
- video_url = compat_urllib_parse.unquote(result.group('url'))
+ video_url = self._search_regex(VIDEO_URL_RE, webpage, u'video url')
+ video_url = compat_urllib_parse.unquote(video_url)
#Get the uploaded date
VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
- result = re.search(VIDEO_UPLOADED_RE, webpage)
- if result is None:
- self._downloader.report_error(u'unable to extract video title')
- return
- upload_date = result.group('date')
+ upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False)
+ if upload_date: upload_date = unified_strdate(upload_date)
info = {'id': video_id,
'url': video_url,
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('videoid')
webpage = self._download_webpage(url, video_id)
# Get the video title
- result = re.search(r'<title>(?P<title>.*)</title>', webpage)
- if result is None:
- raise ExtractorError(u'ERROR: unable to extract video title')
- video_title = result.group('title').strip()
+ video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>',
+ webpage, u'title').strip()
# Get the embed page
result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
webpage = self._download_webpage(embed_page_url, video_id)
# Get the video URL
- result = re.search(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);', webpage)
- if result is None:
- raise ExtractorError(u'ERROR: unable to extract video url')
- video_url = result.group('source')
+ video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);',
+ webpage, u'video URL')
info = {'id': video_id,
'url': video_url,
webpage = self._download_webpage(url, playlist_id)
- m = re.search(r"PAGE.mix = (.*?);\n", webpage, flags=re.DOTALL)
- if not m:
- raise ExtractorError(u'Cannot find trax information')
- json_like = m.group(1)
+ json_like = self._search_regex(r"PAGE.mix = (.*?);\n", webpage, u'trax information', flags=re.DOTALL)
data = json.loads(json_like)
session = str(random.randint(0, 1000000000))
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('videoID')
+
video_url = u'http://cdn.keek.com/keek/video/%s' % video_id
thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
webpage = self._download_webpage(url, video_id)
- m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage)
- title = unescapeHTML(m.group('title'))
- m = re.search(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>', webpage)
- uploader = clean_html(m.group('uploader'))
+
+ video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
+ webpage, u'title')
+
+ uploader = self._html_search_regex(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>',
+ webpage, u'uploader', fatal=False)
+
info = {
'id': video_id,
'url': video_url,
'ext': 'mp4',
- 'title': title,
+ 'title': video_title,
'thumbnail': thumbnail,
'uploader': uploader
}
return [info]
class TEDIE(InfoExtractor):
- _VALID_URL=r'''http://www.ted.com/
+ _VALID_URL=r'''http://www\.ted\.com/
(
((?P<type_playlist>playlists)/(?P<playlist_id>\d+)) # We have a playlist
|
((?P<type_talk>talks)) # We have a simple talk
)
+ (/lang/(.*?))? # The url may contain the language
/(?P<name>\w+) # Here goes the name and then ".html"
'''
# extract values from metadata
url_flv_el = metadata.find('url_flv')
if url_flv_el is None:
- self._downloader.report_error(u'unable to extract download url')
- return
+ raise ExtractorError(u'Unable to extract download url')
video_url = url_flv_el.text
extension = os.path.splitext(video_url)[1][1:]
title_el = metadata.find('title')
if title_el is None:
- self._downloader.report_error(u'unable to extract title')
- return
+ raise ExtractorError(u'Unable to extract title')
title = title_el.text
format_id_el = metadata.find('format_id')
if format_id_el is None:
video_id = m.group('videoID')
webpage = self._download_webpage(url, video_id)
- m = re.search(r'<div class="spVideoTitle">(.*?)</div>', webpage)
- if not m:
- raise ExtractorError(u'Cannot find title')
- video_title = unescapeHTML(m.group(1))
+
+ video_title = self._html_search_regex(r'<div class="module-title">(.*?)</div>',
+ webpage, u'title')
xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml'
xml_code = self._download_webpage(xml_url, video_id,
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.report_error(u'invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('video_id')
webpage = self._download_webpage(url, video_id)
- m = re.search(r'file: "(.*?)",', webpage)
- if not m:
- self._downloader.report_error(u'unable to find video url')
- return
- video_url = m.group(1)
+ video_url = self._search_regex(r'file: "(.*?)",',
+ webpage, u'video URL')
- m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage)
- if not m:
- self._downloader.report_error(u'Cannot find video title')
- title = unescapeHTML(m.group('title')).replace('LiveLeak.com -', '').strip()
+ video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
+ webpage, u'title').replace('LiveLeak.com -', '').strip()
- m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
- if m:
- desc = unescapeHTML(m.group('desc'))
- else:
- desc = None
+ video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
+ webpage, u'description', fatal=False)
- m = re.search(r'By:.*?(\w+)</a>', webpage)
- if m:
- uploader = clean_html(m.group(1))
- else:
- uploader = None
+ video_uploader = self._html_search_regex(r'By:.*?(\w+)</a>',
+ webpage, u'uploader', fatal=False)
info = {
'id': video_id,
'url': video_url,
'ext': 'mp4',
- 'title': title,
- 'description': desc,
- 'uploader': uploader
+ 'title': video_title,
+ 'description': video_description,
+ 'uploader': video_uploader
}
return [info]
streams = [m.groupdict() for m in re.finditer(self._MEDIA_STREAM, html)]
if not streams:
assert '"fsk"' in html
- self._downloader.report_error(u'this video is only available after 8:00 pm')
- return
+ raise ExtractorError(u'This video is only available after 8:00 pm')
# choose default media type and highest quality for now
stream = max([s for s in streams if int(s["media_type"]) == 0],
return [info]
class TumblrIE(InfoExtractor):
- _VALID_URL = r'http://(?P<blog_name>.*?).tumblr.com/((post)|(video))/(?P<id>\d*)/(.*?)'
+ _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)/(.*?)'
def _real_extract(self, url):
m_url = re.match(self._VALID_URL, url)
url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
webpage = self._download_webpage(url, video_id)
- re_video = r'src=\\x22(?P<video_url>http://%s.tumblr.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id)
+ re_video = r'src=\\x22(?P<video_url>http://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id)
video = re.search(re_video, webpage)
if video is None:
- self.to_screen("No video founded")
- return []
+ raise ExtractorError(u'Unable to extract video')
video_url = video.group('video_url')
ext = video.group('ext')
- re_thumb = r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22' # We pick the first poster
- thumb = re.search(re_thumb, webpage).group('thumb').replace('\\', '')
+ video_thumbnail = self._search_regex(r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22',
+ webpage, u'thumbnail', fatal=False) # We pick the first poster
+ if video_thumbnail: video_thumbnail = video_thumbnail.replace('\\', '')
# The only place where you can get a title, it's not complete,
# but searching in other places doesn't work for all videos
- re_title = r'<title>(.*?) - (?P<title>.*?)</title>'
- title = unescapeHTML(re.search(re_title, webpage).group('title'))
+ video_title = self._html_search_regex(r'<title>(?P<title>.*?)</title>',
+ webpage, u'title', flags=re.DOTALL)
return [{'id': video_id,
'url': video_url,
- 'title': title,
- 'thumbnail': thumb,
+ 'title': video_title,
+ 'thumbnail': video_thumbnail,
'ext': ext
}]
+class BandcampIE(InfoExtractor):
+ _VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ title = mobj.group('title')
+ webpage = self._download_webpage(url, title)
+ # We get the link to the free download page
+ m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
+ if m_download is None:
+ raise ExtractorError(u'No free songs found')
+
+ download_link = m_download.group(1)
+ id = re.search(r'var TralbumData = {(.*?)id: (?P<id>\d*?)$',
+ webpage, re.MULTILINE|re.DOTALL).group('id')
+
+ download_webpage = self._download_webpage(download_link, id,
+ 'Downloading free downloads page')
+ # We get the dictionary of the track from some javascrip code
+ info = re.search(r'items: (.*?),$',
+ download_webpage, re.MULTILINE).group(1)
+ info = json.loads(info)[0]
+ # We pick mp3-320 for now, until format selection can be easily implemented.
+ mp3_info = info[u'downloads'][u'mp3-320']
+ # If we try to use this url it says the link has expired
+ initial_url = mp3_info[u'url']
+ re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$'
+ m_url = re.match(re_url, initial_url)
+ #We build the url we will use to get the final track url
+ # This url is build in Bandcamp in the script download_bunde_*.js
+ request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), id, m_url.group('ts'))
+ final_url_webpage = self._download_webpage(request_url, id, 'Requesting download url')
+ # If we could correctly generate the .rand field the url would be
+ #in the "download_url" key
+ final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1)
+
+ track_info = {'id':id,
+ 'title' : info[u'title'],
+ 'ext' : 'mp3',
+ 'url' : final_url,
+ 'thumbnail' : info[u'thumb_url'],
+ 'uploader' : info[u'artist']
+ }
+
+ return [track_info]
+
+class RedTubeIE(InfoExtractor):
+ """Information Extractor for redtube"""
+ _VALID_URL = r'(?:http://)?(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
+
+ def _real_extract(self,url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+
+ video_id = mobj.group('id')
+ video_extension = 'mp4'
+ webpage = self._download_webpage(url, video_id)
+
+ self.report_extraction(video_id)
+
+ video_url = self._html_search_regex(r'<source src="(.+?)" type="video/mp4">',
+ webpage, u'video URL')
+
+ video_title = self._html_search_regex('<h1 class="videoTitle slidePanelMovable">(.+?)</h1>',
+ webpage, u'title')
+
+ return [{
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': video_extension,
+ 'title': video_title,
+ }]
+
+class InaIE(InfoExtractor):
+ """Information Extractor for Ina.fr"""
+ _VALID_URL = r'(?:http://)?(?:www\.)?ina\.fr/video/(?P<id>I[0-9]+)/.*'
+
+ def _real_extract(self,url):
+ mobj = re.match(self._VALID_URL, url)
+
+ video_id = mobj.group('id')
+ mrss_url='http://player.ina.fr/notices/%s.mrss' % video_id
+ video_extension = 'mp4'
+ webpage = self._download_webpage(mrss_url, video_id)
+
+ self.report_extraction(video_id)
+
+ video_url = self._html_search_regex(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)',
+ webpage, u'video URL')
+
+ video_title = self._search_regex(r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>',
+ webpage, u'title')
+
+ return [{
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': video_extension,
+ 'title': video_title,
+ }]
+
+class HowcastIE(InfoExtractor):
+ """Information Extractor for Howcast.com"""
+ _VALID_URL = r'(?:https?://)?(?:www\.)?howcast\.com/videos/(?P<id>\d+)'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+
+ video_id = mobj.group('id')
+ webpage_url = 'http://www.howcast.com/videos/' + video_id
+ webpage = self._download_webpage(webpage_url, video_id)
+
+ self.report_extraction(video_id)
+
+ video_url = self._search_regex(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)',
+ webpage, u'video URL')
+
+ video_title = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') property=\'og:title\'',
+ webpage, u'title')
+
+ video_description = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'',
+ webpage, u'description', fatal=False)
+
+ thumbnail = self._html_search_regex(r'<meta content=\'(.+?)\' property=\'og:image\'',
+ webpage, u'thumbnail', fatal=False)
+
+ return [{
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': video_title,
+ 'description': video_description,
+ 'thumbnail': thumbnail,
+ }]
+
+class VineIE(InfoExtractor):
+ """Information Extractor for Vine.co"""
+ _VALID_URL = r'(?:https?://)?(?:www\.)?vine\.co/v/(?P<id>\w+)'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+
+ video_id = mobj.group('id')
+ webpage_url = 'https://vine.co/v/' + video_id
+ webpage = self._download_webpage(webpage_url, video_id)
+
+ self.report_extraction(video_id)
+
+ video_url = self._html_search_regex(r'<meta property="twitter:player:stream" content="(.+?)"',
+ webpage, u'video URL')
+
+ video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
+ webpage, u'title')
+
+ thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)(\?.*?)?"',
+ webpage, u'thumbnail', fatal=False)
+
+ uploader = self._html_search_regex(r'<div class="user">.*?<h2>(.+?)</h2>',
+ webpage, u'uploader', fatal=False, flags=re.DOTALL)
+
+ return [{
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': video_title,
+ 'thumbnail': thumbnail,
+ 'uploader': uploader,
+ }]
+
+class FlickrIE(InfoExtractor):
+ """Information Extractor for Flickr videos"""
+ _VALID_URL = r'(?:https?://)?(?:www\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+
+ video_id = mobj.group('id')
+ video_uploader_id = mobj.group('uploader_id')
+ webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_id
+ webpage = self._download_webpage(webpage_url, video_id)
+
+ secret = self._search_regex(r"photo_secret: '(\w+)'", webpage, u'secret')
+
+ first_url = 'https://secure.flickr.com/apps/video/video_mtl_xml.gne?v=x&photo_id=' + video_id + '&secret=' + secret + '&bitrate=700&target=_self'
+ first_xml = self._download_webpage(first_url, video_id, 'Downloading first data webpage')
+
+ node_id = self._html_search_regex(r'<Item id="id">(\d+-\d+)</Item>',
+ first_xml, u'node_id')
+
+ second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1'
+ second_xml = self._download_webpage(second_url, video_id, 'Downloading second data webpage')
+
+ self.report_extraction(video_id)
+
+ mobj = re.search(r'<STREAM APP="(.+?)" FULLPATH="(.+?)"', second_xml)
+ if mobj is None:
+ raise ExtractorError(u'Unable to extract video url')
+ video_url = mobj.group(1) + unescapeHTML(mobj.group(2))
+
+ video_title = self._html_search_regex(r'<meta property="og:title" content=(?:"([^"]+)"|\'([^\']+)\')',
+ webpage, u'video title')
+
+ video_description = self._html_search_regex(r'<meta property="og:description" content=(?:"([^"]+)"|\'([^\']+)\')',
+ webpage, u'description', fatal=False)
+
+ thumbnail = self._html_search_regex(r'<meta property="og:image" content=(?:"([^"]+)"|\'([^\']+)\')',
+ webpage, u'thumbnail', fatal=False)
+
+ return [{
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': video_title,
+ 'description': video_description,
+ 'thumbnail': thumbnail,
+ 'uploader_id': video_uploader_id,
+ }]
+
+class TeamcocoIE(InfoExtractor):
+ _VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+ url_title = mobj.group('url_title')
+ webpage = self._download_webpage(url, url_title)
+
+ video_id = self._html_search_regex(r'<article class="video" data-id="(\d+?)"',
+ webpage, u'video id')
+
+ self.report_extraction(video_id)
+
+ video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
+ webpage, u'title')
+
+ thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)"',
+ webpage, u'thumbnail', fatal=False)
+
+ video_description = self._html_search_regex(r'<meta property="og:description" content="(.*?)"',
+ webpage, u'description', fatal=False)
+
+ data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
+ data = self._download_webpage(data_url, video_id, 'Downloading data webpage')
+
+ video_url = self._html_search_regex(r'<file type="high".*?>(.*?)</file>',
+ data, u'video URL')
+
+ return [{
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': video_title,
+ 'thumbnail': thumbnail,
+ 'description': video_description,
+ }]
+
+class XHamsterIE(InfoExtractor):
+ """Information Extractor for xHamster"""
+ _VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P<id>[0-9]+)/.*\.html'
+
+ def _real_extract(self,url):
+ mobj = re.match(self._VALID_URL, url)
+
+ video_id = mobj.group('id')
+ mrss_url = 'http://xhamster.com/movies/%s/.html' % video_id
+ webpage = self._download_webpage(mrss_url, video_id)
+
+ mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
+ if mobj is None:
+ raise ExtractorError(u'Unable to extract media URL')
+ if len(mobj.group('server')) == 0:
+ video_url = compat_urllib_parse.unquote(mobj.group('file'))
+ else:
+ video_url = mobj.group('server')+'/key='+mobj.group('file')
+ video_extension = video_url.split('.')[-1]
+
+ video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
+ webpage, u'title')
+
+ # Can't see the description anywhere in the UI
+ # video_description = self._html_search_regex(r'<span>Description: </span>(?P<description>[^<]+)',
+ # webpage, u'description', fatal=False)
+ # if video_description: video_description = unescapeHTML(video_description)
+
+ mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
+ if mobj:
+ video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
+ else:
+ video_upload_date = None
+ self._downloader.report_warning(u'Unable to extract upload date')
+
+ video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
+ webpage, u'uploader id', default=u'anonymous')
+
+ video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
+ webpage, u'thumbnail', fatal=False)
+
+ return [{
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': video_extension,
+ 'title': video_title,
+ # 'description': video_description,
+ 'upload_date': video_upload_date,
+ 'uploader_id': video_uploader_id,
+ 'thumbnail': video_thumbnail
+ }]
+
+class HypemIE(InfoExtractor):
+ """Information Extractor for hypem"""
+ _VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+ track_id = mobj.group(1)
+
+ data = { 'ax': 1, 'ts': time.time() }
+ data_encoded = compat_urllib_parse.urlencode(data)
+ complete_url = url + "?" + data_encoded
+ request = compat_urllib_request.Request(complete_url)
+ response, urlh = self._download_webpage_handle(request, track_id, u'Downloading webpage with the url')
+ cookie = urlh.headers.get('Set-Cookie', '')
+
+ self.report_extraction(track_id)
+
+ html_tracks = self._html_search_regex(r'<script type="application/json" id="displayList-data">(.*?)</script>',
+ response, u'tracks', flags=re.MULTILINE|re.DOTALL).strip()
+ try:
+ track_list = json.loads(html_tracks)
+ track = track_list[u'tracks'][0]
+ except ValueError:
+ raise ExtractorError(u'Hypemachine contained invalid JSON.')
+
+ key = track[u"key"]
+ track_id = track[u"id"]
+ artist = track[u"artist"]
+ title = track[u"song"]
+
+ serve_url = "http://hypem.com/serve/source/%s/%s" % (compat_str(track_id), compat_str(key))
+ request = compat_urllib_request.Request(serve_url, "" , {'Content-Type': 'application/json'})
+ request.add_header('cookie', cookie)
+ song_data_json = self._download_webpage(request, track_id, u'Downloading metadata')
+ try:
+ song_data = json.loads(song_data_json)
+ except ValueError:
+ raise ExtractorError(u'Hypemachine contained invalid JSON.')
+ final_url = song_data[u"url"]
+
+ return [{
+ 'id': track_id,
+ 'url': final_url,
+ 'ext': "mp3",
+ 'title': title,
+ 'artist': artist,
+ }]
+
def gen_extractors():
""" Return a list of an instance of every supported extractor.
YahooSearchIE(),
DepositFilesIE(),
FacebookIE(),
- BlipTVUserIE(),
BlipTVIE(),
+ BlipTVUserIE(),
VimeoIE(),
MyVideoIE(),
ComedyCentralIE(),
LiveLeakIE(),
ARDIE(),
TumblrIE(),
+ BandcampIE(),
+ RedTubeIE(),
+ InaIE(),
+ HowcastIE(),
+ VineIE(),
+ FlickrIE(),
+ TeamcocoIE(),
+ XHamsterIE(),
+ HypemIE(),
GenericIE()
]