X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=37f9c1449d5be600ff2b42748cfbef122cf0952c;hb=1142d311648fe96b0a444a9291233e31e443da41;hp=6a6545c9b578fba948962542d602bc5352b86840;hpb=44696667805343a2f60bdec25d8ab9ed90b5963c;p=youtube-dl.git diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 6a6545c9b..37f9c1449 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -16,6 +16,9 @@ import xml.etree.ElementTree import random import math import operator +import hashlib +import binascii +import urllib from .utils import * @@ -114,8 +117,8 @@ class InfoExtractor(object): 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) @@ -124,8 +127,8 @@ class InfoExtractor(object): 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) @@ -142,7 +145,12 @@ class InfoExtractor(object): 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]'""" @@ -152,6 +160,10 @@ class InfoExtractor(object): """Report information extraction.""" self.to_screen(u'%s: Extracting information' % id_or_name) + def report_download_webpage(self, video_id): + """Report webpage download.""" + self.to_screen(u'%s: Downloading webpage' % video_id) + def report_age_confirmation(self): """Report attempt to confirm age.""" self.to_screen(u'Confirming age') @@ -179,6 +191,45 @@ class InfoExtractor(object): video_info['title'] = playlist_title return video_info +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|[1-9][0-9]*|all):(?P[\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.""" @@ -202,7 +253,7 @@ class YoutubeIE(InfoExtractor): ([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=([^&]+)' @@ -325,6 +376,34 @@ class YoutubeIE(InfoExtractor): 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: @@ -418,7 +497,7 @@ class YoutubeIE(InfoExtractor): # 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, @@ -463,14 +542,12 @@ class YoutubeIE(InfoExtractor): 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 @@ -478,18 +555,17 @@ class YoutubeIE(InfoExtractor): # 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') @@ -513,23 +589,20 @@ class YoutubeIE(InfoExtractor): 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 @@ -542,8 +615,7 @@ class YoutubeIE(InfoExtractor): # 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 @@ -558,19 +630,18 @@ class YoutubeIE(InfoExtractor): mobj = re.search(r'id="eow-date.*?>(.*?)', 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_description: video_description = clean_html(video_description) else: - video_description = '' + fd_mobj = re.search(r'= 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 @@ -680,17 +761,10 @@ class MetacafeIE(InfoExtractor): _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') - def report_download_webpage(self, video_id): - """Report webpage download.""" - self.to_screen(u'%s: Downloading webpage' % video_id) - def _real_initialize(self): # Retrieve disclaimer request = compat_urllib_request.Request(self._DISCLAIMER) @@ -698,8 +772,7 @@ class MetacafeIE(InfoExtractor): 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 = { @@ -711,15 +784,13 @@ class MetacafeIE(InfoExtractor): 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) @@ -748,30 +819,25 @@ class MetacafeIE(InfoExtractor): 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":"(?Phttp.*?)",(.*?)"key":"(?P.*?)"', 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)(.*) - Video', 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 [{ @@ -783,23 +849,17 @@ class MetacafeIE(InfoExtractor): '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] @@ -814,8 +874,7 @@ class DailymotionIE(InfoExtractor): 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']: @@ -824,13 +883,11 @@ class DailymotionIE(InfoExtractor): 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('\\/', '/') @@ -838,8 +895,7 @@ class DailymotionIE(InfoExtractor): mobj = re.search(r'', 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 @@ -872,50 +928,52 @@ class DailymotionIE(InfoExtractor): 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.*)\.(?P(flv)|(mp4))' IE_NAME = u'photobucket' - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self.to_screen(u'%s: Downloading webpage' % video_id) - 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) + # We try first by looking the javascript code: + mobj = re.search(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (?P.*?)\);', 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'], + }] + + # We try looking in other parts of the webpage mobj = re.search(r'', webpage) if mobj is None: - self._downloader.report_error(u'unable to extract media URL') - return + raise ExtractorError(u'Unable to extract media URL') mediaURL = compat_urllib_parse.unquote(mobj.group(1)) video_url = mediaURL mobj = re.search(r'(.*) video by (.*) - Photobucket', 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') @@ -931,180 +989,95 @@ class PhotobucketIE(InfoExtractor): 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\d*?)\.html' - def report_download_webpage(self, video_id): - """Report webpage download.""" - self.to_screen(u'%s: Downloading webpage' % video_id) - - 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'', 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'

(.*)

', 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'', 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'', 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'', 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'', 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'.+?)";', 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'''<!\[CDATA\[(?P<title>.*?)\]\]>.* + .*?)\]\]>.* + .*?)\ .*\]\]>.* + https?://)?(?:(?:www|player)\.)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?Pplay_redirect_hls\?clip_id=)?(?:videos?/)?(?P[0-9]+)' + _VALID_URL = r'(?Phttps?://)?(?:(?:www|player)\.)?vimeo(?Ppro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?Pplay_redirect_hls\?clip_id=)?(?:videos?/)?(?P[0-9]+)' IE_NAME = u'vimeo' - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self.to_screen(u'%s: Downloading webpage' % video_id) - 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, @@ -1116,15 +1089,17 @@ class VimeoIE(InfoExtractor): 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"] @@ -1166,8 +1141,7 @@ class VimeoIE(InfoExtractor): 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()) @@ -1193,24 +1167,15 @@ class ArteTvIE(InfoExtractor): IE_NAME = u'arte.tv' - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self.to_screen(u'%s: Downloading webpage' % video_id) - 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): @@ -1219,13 +1184,11 @@ class ArteTvIE(InfoExtractor): 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.trouble(err) - return + raise ExtractorError(err) else: info[key] = mobj.group(i) @@ -1238,7 +1201,7 @@ class ArteTvIE(InfoExtractor): r'src="(.*?/videothek_js.*?\.js)', 0, [ - (1, 'url', u'ERROR: Invalid URL: %s' % url) + (1, 'url', u'Invalid URL: %s' % url) ] ) http_host = url.split('/')[2] @@ -1250,9 +1213,9 @@ class ArteTvIE(InfoExtractor): '(rtmp://.*?)\'', re.DOTALL, [ - (1, 'path', u'ERROR: could not extract video path: %s' % url), - (2, 'player', u'ERROR: could not extract video player: %s' % url), - (3, 'url', u'ERROR: could not extract video url: %s' % url) + (1, 'path', u'could not extract video path: %s' % url), + (2, 'player', u'could not extract video player: %s' % url), + (3, 'url', u'could not extract video url: %s' % url) ] ) video_url = u'%s/%s' % (info.get('url'), info.get('path')) @@ -1264,7 +1227,7 @@ class ArteTvIE(InfoExtractor): r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)', 0, [ - (1, 'url', u'ERROR: Invalid URL: %s' % url) + (1, 'url', u'Invalid URL: %s' % url) ] ) next_url = compat_urllib_parse.unquote(info.get('url')) @@ -1273,7 +1236,7 @@ class ArteTvIE(InfoExtractor): r'