import xml.etree.ElementTree
import random
import math
-import urllib
-import urllib2
-import httplib
-from urlparse import parse_qs, urlparse
from .utils import *
(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
|(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))))
$"""
- IE_NAME = u'comedycentral'
_available_formats = ['3500', '2200', '1700', '1200', '750', '400']
def report_extraction(self, episode_id):
self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
- def report_config_download(self, episode_id):
- self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id)
+ def report_config_download(self, episode_id, media_id):
+ self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration for %s' % (episode_id, media_id))
def report_index_download(self, episode_id):
self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id)
- def report_player_url(self, episode_id):
- self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id)
-
-
def _print_formats(self, formats):
print('Available formats:')
for x in formats:
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.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
return
return
epTitle = mobj.group('episode')
- mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', html)
+ mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
if len(mMovieParams) == 0:
# The Colbert Report embeds the information in a without
# a URL prefix; so extract the alternate reference
# and then add the URL prefix manually.
- altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', html)
+ altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
if len(altMovieParams) == 0:
self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
return
else:
mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
- playerUrl_raw = mMovieParams[0][0]
- self.report_player_url(epTitle)
- try:
- urlHandle = compat_urllib_request.urlopen(playerUrl_raw)
- playerUrl = urlHandle.geturl()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to find out player URL: ' + compat_str(err))
- return
-
uri = mMovieParams[0][1]
indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
self.report_index_download(epTitle)
idoc = xml.etree.ElementTree.fromstring(indexXml)
itemEls = idoc.findall('.//item')
- for itemEl in itemEls:
+ for partNum,itemEl in enumerate(itemEls):
mediaId = itemEl.findall('./guid')[0].text
shortMediaId = mediaId.split(':')[-1]
showId = mediaId.split(':')[-2].replace('.com', '')
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)
+ 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:
return
# For now, just pick the highest bitrate
- format,video_url = turls[-1]
+ format,rtmp_video_url = turls[-1]
# Get the format arg from the arg stream
req_format = self._downloader.params.get('format', None)
# Select format if we can find one
for f,v in turls:
if f == req_format:
- format, video_url = f, v
+ format, rtmp_video_url = f, v
break
- # Patch to download from alternative CDN, which does not
- # break on current RTMPDump builds
- broken_cdn = "rtmpe://viacomccstrmfs.fplive.net/viacomccstrm/gsp.comedystor/"
- better_cdn = "rtmpe://cp10740.edgefcs.net/ondemand/mtvnorigin/gsp.comedystor/"
+ m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url)
+ if not m:
+ raise ExtractorError(u'Cannot transform RTMP url')
+ base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
+ video_url = base + m.group('finalid')
- if video_url.startswith(broken_cdn):
- video_url = video_url.replace(broken_cdn, better_cdn)
-
- effTitle = showId + u'-' + epTitle
+ effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1)
info = {
'id': shortMediaId,
'url': video_url,
'format': format,
'thumbnail': None,
'description': officialTitle,
- 'player_url': None #playerUrl
}
-
results.append(info)
return results
return [info]
-
class CollegeHumorIE(InfoExtractor):
"""Information extractor for collegehumor.com"""
return
response = json.loads(webpage)
+ if type(response) != list:
+ error_text = response.get('error', 'unknown error')
+ self._downloader.trouble(u'ERROR: Justin.tv API: %s' % error_text)
+ return
info = []
for clip in response:
video_url = clip['video_file_url']
if video_url:
video_extension = os.path.splitext(video_url)[1][1:]
- video_date = re.sub('-', '', clip['created_on'][:10])
+ video_date = re.sub('-', '', clip['start_time'][:10])
+ video_uploader_id = clip.get('user_id', clip.get('channel_id'))
info.append({
'id': clip['id'],
'url': video_url,
'title': clip['title'],
- 'uploader': clip.get('user_id', clip.get('channel_id')),
+ 'uploader': clip.get('channel_name', video_uploader_id),
+ 'uploader_id': video_uploader_id,
'upload_date': video_date,
'ext': video_extension,
})
paged = True
api += '/channel/archives/%s.json'
else:
- api += '/clip/show/%s.json'
+ api += '/broadcast/by_archive/%s.json'
api = api % (video_id,)
self.report_extraction(video_id)
}
videos.append(info)
return videos
-
+
class UstreamIE(InfoExtractor):
- _VALID_URL = r'http://www.ustream.tv/recorded/(?P<videoID>\d+)'
+ _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)'
IE_NAME = u'ustream'
-
+
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('videoID')
"""Information extractor for youporn.com."""
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)'
- IE_NAME = u'youporn'
- VIDEO_TITLE_RE = r'videoTitleArea">(?P<title>.*)</h1>'
- VIDEO_DATE_RE = r'Date:</b>(?P<date>.*)</li>'
- VIDEO_UPLOADER_RE = r'Submitted:</b>(?P<uploader>.*)</li>'
- DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
- LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
-
+
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
- def report_id(self, video_id):
- """Report finding video ID"""
- self._downloader.to_screen(u'[youporn] Video ID: %s' % video_id)
+ # def report_id(self, video_id):
+ # """Report finding video ID"""
+ # self._downloader.to_screen(u'[youporn] Video ID: %s' % video_id)
- def report_webpage(self, url):
- """Report downloading page"""
- self._downloader.to_screen(u'[youporn] Downloaded page: %s' % url)
+ # def report_webpage(self, url):
+ # """Report downloading page"""
+ # self._downloader.to_screen(u'[youporn] Downloaded page: %s' % url)
- def report_title(self, video_title):
- """Report dfinding title"""
- self._downloader.to_screen(u'[youporn] Title: %s' % video_title)
+ # def report_title(self, video_title):
+ # """Report dfinding title"""
+ # self._downloader.to_screen(u'[youporn] Title: %s' % video_title)
- def report_uploader(self, uploader):
- """Report dfinding title"""
- self._downloader.to_screen(u'[youporn] Uploader: %s' % uploader)
+ # def report_uploader(self, uploader):
+ # """Report dfinding title"""
+ # self._downloader.to_screen(u'[youporn] Uploader: %s' % uploader)
- def report_upload_date(self, video_date):
- """Report finding date"""
- self._downloader.to_screen(u'[youporn] Date: %s' % video_date)
+ # def report_upload_date(self, video_date):
+ # """Report finding date"""
+ # self._downloader.to_screen(u'[youporn] Date: %s' % video_date)
def _print_formats(self, formats):
"""Print all available formats"""
- print 'Available formats:'
- print u'ext\t\tformat'
- print u'---------------------------------'
+ print('Available formats:')
+ print(u'ext\t\tformat')
+ print(u'---------------------------------')
for format in formats:
- print u'%s\t\t%s' % (format['ext'], format['format'])
+ print(u'%s\t\t%s' % (format['ext'], format['format']))
def _specific(self, req_format, formats):
for x in formats:
return x
return None
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
- video_id = mobj.group('videoid').decode('utf-8')
- self.report_id(video_id)
+ video_id = mobj.group('videoid')
+ #self.report_id(video_id)
- # Get webpage content
- try:
- webpage = urllib2.urlopen(url).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err)
- return
- self.report_webpage(url)
+ webpage = self._download_webpage(url, video_id)
+ #self.report_webpage(url)
# Get the video title
- result = re.search(self.VIDEO_TITLE_RE, webpage)
+ VIDEO_TITLE_RE = r'videoTitleArea">(?P<title>.*)</h1>'
+ result = re.search(VIDEO_TITLE_RE, webpage)
if result is None:
self._downloader.trouble(u'ERROR: unable to extract video title')
return
- video_title = result.group('title').decode('utf-8').strip()
- self.report_title(video_title)
+ video_title = result.group('title').strip()
+ #self.report_title(video_title)
# Get the video date
- result = re.search(self.VIDEO_DATE_RE, webpage)
+ VIDEO_DATE_RE = r'Date:</b>(?P<date>.*)</li>'
+ result = re.search(VIDEO_DATE_RE, webpage)
if result is None:
self._downloader.trouble(u'ERROR: unable to extract video date')
return
- upload_date = result.group('date').decode('utf-8').strip()
- self.report_upload_date(upload_date)
+ upload_date = result.group('date').strip()
+ #self.report_upload_date(upload_date)
# Get the video uploader
- result = re.search(self.VIDEO_UPLOADER_RE, webpage)
+ VIDEO_UPLOADER_RE = r'Submitted:</b>(?P<uploader>.*)</li>'
+ result = re.search(VIDEO_UPLOADER_RE, webpage)
if result is None:
self._downloader.trouble(u'ERROR: unable to extract uploader')
return
- video_uploader = result.group('uploader').decode('utf-8').strip()
+ video_uploader = result.group('uploader').strip()
video_uploader = clean_html( video_uploader )
- self.report_uploader(video_uploader)
+ #self.report_uploader(video_uploader)
# Get all of the formats available
- result = re.search(self.DOWNLOAD_LIST_RE, webpage)
+ DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
+ result = re.search(DOWNLOAD_LIST_RE, webpage)
if result is None:
self._downloader.trouble(u'ERROR: unable to extract download list')
return
- download_list_html = result.group('download_list').decode('utf-8').strip()
+ download_list_html = result.group('download_list').strip()
# Get all of the links from the page
- links = re.findall(self.LINK_RE, download_list_html)
+ LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
+ links = re.findall(LINK_RE, download_list_html)
if(len(links) == 0):
self._downloader.trouble(u'ERROR: no known formats available for video')
return
# http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0
# A path looks like this:
# /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
- video_url = unescapeHTML( link.decode('utf-8') )
- path = urlparse( video_url ).path
+ video_url = unescapeHTML( link )
+ path = compat_urllib_parse_urlparse( video_url ).path
extension = os.path.splitext( path )[1][1:]
format = path.split('/')[4].split('_')[:2]
size = format[0]
"""Information extractor for pornotube.com."""
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
- IE_NAME = u'pornotube'
- VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",'
- VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
+ # def __init__(self, downloader=None):
+ # InfoExtractor.__init__(self, downloader)
- def report_extract_entry(self, url):
- """Report downloading extry"""
- self._downloader.to_screen(u'[pornotube] Downloading entry: %s' % url.decode('utf-8'))
+ # def report_extract_entry(self, url):
+ # """Report downloading extry"""
+ # self._downloader.to_screen(u'[pornotube] Downloading entry: %s' % url.decode('utf-8'))
- def report_date(self, upload_date):
- """Report finding uploaded date"""
- self._downloader.to_screen(u'[pornotube] Entry date: %s' % upload_date)
+ # def report_date(self, upload_date):
+ # """Report finding uploaded date"""
+ # self._downloader.to_screen(u'[pornotube] Entry date: %s' % upload_date)
- def report_webpage(self, url):
- """Report downloading page"""
- self._downloader.to_screen(u'[pornotube] Downloaded page: %s' % url)
+ # def report_webpage(self, url):
+ # """Report downloading page"""
+ # self._downloader.to_screen(u'[pornotube] Downloaded page: %s' % url)
- def report_title(self, video_title):
- """Report downloading extry"""
- self._downloader.to_screen(u'[pornotube] Title: %s' % video_title.decode('utf-8'))
+ # def report_title(self, video_title):
+ # """Report downloading extry"""
+ # self._downloader.to_screen(u'[pornotube] Title: %s' % video_title.decode('utf-8'))
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
- video_id = mobj.group('videoid').decode('utf-8')
- video_title = mobj.group('title').decode('utf-8')
- self.report_title(video_title);
+ video_id = mobj.group('videoid')
+ video_title = mobj.group('title')
+ #self.report_title(video_title);
# Get webpage content
- try:
- webpage = urllib2.urlopen(url).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err)
- return
- self.report_webpage(url)
+ webpage = self._download_webpage(url, video_id)
+ #self.report_webpage(url)
# Get the video URL
- result = re.search(self.VIDEO_URL_RE, webpage)
+ 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.trouble(u'ERROR: unable to extract video url')
return
- video_url = urllib.unquote(result.group('url').decode('utf-8'))
- self.report_extract_entry(video_url)
+ video_url = compat_urllib_parse.unquote(result.group('url'))
+ #self.report_extract_entry(video_url)
#Get the uploaded date
- result = re.search(self.VIDEO_UPLOADED_RE, webpage)
+ 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.trouble(u'ERROR: unable to extract video title')
return
- upload_date = result.group('date').decode('utf-8')
- self.report_date(upload_date);
-
+ upload_date = result.group('date')
+ #self.report_date(upload_date);
info = {'id': video_id,
'url': video_url,
class YouJizzIE(InfoExtractor):
"""Information extractor for youjizz.com."""
- _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/([^.]+).html$'
- IE_NAME = u'youjizz'
- VIDEO_TITLE_RE = r'<title>(?P<title>.*)</title>'
- EMBED_PAGE_RE = r'http://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)'
- SOURCE_RE = r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);'
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
- def report_extract_entry(self, url):
- """Report downloading extry"""
- self._downloader.to_screen(u'[youjizz] Downloading entry: %s' % url.decode('utf-8'))
+ # def report_extract_entry(self, url):
+ # """Report downloading extry"""
+ # self._downloader.to_screen(u'[youjizz] Downloading entry: %s' % url.decode('utf-8'))
- def report_webpage(self, url):
- """Report downloading page"""
- self._downloader.to_screen(u'[youjizz] Downloaded page: %s' % url)
+ # def report_webpage(self, url):
+ # """Report downloading page"""
+ # self._downloader.to_screen(u'[youjizz] Downloaded page: %s' % url)
- def report_title(self, video_title):
- """Report downloading extry"""
- self._downloader.to_screen(u'[youjizz] Title: %s' % video_title.decode('utf-8'))
+ # def report_title(self, video_title):
+ # """Report downloading extry"""
+ # self._downloader.to_screen(u'[youjizz] Title: %s' % video_title.decode('utf-8'))
- def report_embed_page(self, embed_page):
- """Report downloading extry"""
- self._downloader.to_screen(u'[youjizz] Embed Page: %s' % embed_page.decode('utf-8'))
+ # def report_embed_page(self, embed_page):
+ # """Report downloading extry"""
+ # self._downloader.to_screen(u'[youjizz] Embed Page: %s' % embed_page.decode('utf-8'))
def _real_extract(self, url):
- # Get webpage content
- try:
- webpage = urllib2.urlopen(url).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err)
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
- self.report_webpage(url)
+
+ video_id = mobj.group('videoid')
+
+ # Get webpage content
+ webpage = self._download_webpage(url, video_id)
+ #self.report_webpage(url)
# Get the video title
- result = re.search(self.VIDEO_TITLE_RE, webpage)
+ VIDEO_TITLE_RE = r'<title>(?P<title>.*)</title>'
+ result = re.search(VIDEO_TITLE_RE, webpage)
if result is None:
self._downloader.trouble(u'ERROR: unable to extract video title')
return
- video_title = result.group('title').decode('utf-8').strip()
- self.report_title(video_title)
+ video_title = result.group('title').strip()
+ #self.report_title(video_title)
# Get the embed page
- result = re.search(self.EMBED_PAGE_RE, webpage)
+ EMBED_PAGE_RE = r'http://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)'
+ result = re.search(EMBED_PAGE_RE, webpage)
if result is None:
self._downloader.trouble(u'ERROR: unable to extract embed page')
return
- embed_page_url = result.group(0).decode('utf-8').strip()
- video_id = result.group('videoid').decode('utf-8')
- self.report_embed_page(embed_page_url)
+ embed_page_url = result.group(0).strip()
+ video_id = result.group('videoid')
+ #self.report_embed_page(embed_page_url)
- try:
- webpage = urllib2.urlopen(embed_page_url).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download video embed page: %s' % err)
- return
-
+ webpage = self._download_webpage(embed_page_url, video_id)
+
# Get the video URL
- result = re.search(self.SOURCE_RE, webpage)
+ SOURCE_RE = r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);'
+ result = re.search(SOURCE_RE, webpage)
if result is None:
self._downloader.trouble(u'ERROR: unable to extract video url')
return
- video_url = result.group('source').decode('utf-8')
- self.report_extract_entry(video_url)
+ video_url = result.group('source')
+ #self.report_extract_entry(video_url)
info = {'id': video_id,
'url': video_url,
projects / youtube-dl.git / blobdiff