X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=ff1f07e9b80a35705f4474a59b39df00d578ae72;hb=c681a03918a8f67f25e3ae7cc4140b76d6a73578;hp=cca7e1b54be0766bdf3086b25ba25a85f2819e98;hpb=fa41fbd3189b36300a4558b722dea5857a7e4214;p=youtube-dl diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index cca7e1b54..ff1f07e9b 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -115,7 +115,8 @@ class InfoExtractor(object): """ Returns the response handle """ if note is None: note = u'Downloading video webpage' - self._downloader.to_screen(u'[%s] %s: %s' % (self.IE_NAME, video_id, note)) + if note is not False: + self.to_screen(u'%s: %s' % (video_id, note)) try: return compat_urllib_request.urlopen(url_or_request) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: @@ -133,8 +134,51 @@ class InfoExtractor(object): else: encoding = 'utf-8' webpage_bytes = urlh.read() + if self._downloader.params.get('dump_intermediate_pages', False): + try: + url = url_or_request.get_full_url() + except AttributeError: + url = url_or_request + 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') + def to_screen(self, msg): + """Print msg to screen, prefixing it with '[ie_name]'""" + self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg)) + + def report_extraction(self, id_or_name): + """Report information extraction.""" + self.to_screen(u'%s: Extracting information' % id_or_name) + + def report_age_confirmation(self): + """Report attempt to confirm age.""" + self.to_screen(u'Confirming age') + + #Methods for following #608 + #They set the correct value of the '_type' key + def video_result(self, video_info): + """Returns a video""" + video_info['_type'] = 'video' + return video_info + def url_result(self, url, ie=None): + """Returns a url that points to a page that should be processed""" + #TODO: ie should be the class used for getting the info + video_info = {'_type': 'url', + 'url': url, + 'ie_key': ie} + return video_info + def playlist_result(self, entries, playlist_id=None, playlist_title=None): + """Returns a playlist""" + video_info = {'_type': 'playlist', + 'entries': entries} + if playlist_id: + video_info['id'] = playlist_id + if playlist_title: + video_info['title'] = playlist_title + return video_info + class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" @@ -204,48 +248,44 @@ class YoutubeIE(InfoExtractor): def report_lang(self): """Report attempt to set language.""" - self._downloader.to_screen(u'[youtube] Setting language') + self.to_screen(u'Setting language') def report_login(self): """Report attempt to log in.""" - self._downloader.to_screen(u'[youtube] Logging in') - - def report_age_confirmation(self): - """Report attempt to confirm age.""" - self._downloader.to_screen(u'[youtube] Confirming age') + self.to_screen(u'Logging in') def report_video_webpage_download(self, video_id): """Report attempt to download video webpage.""" - self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id) + self.to_screen(u'%s: Downloading video webpage' % video_id) def report_video_info_webpage_download(self, video_id): """Report attempt to download video info webpage.""" - self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id) + self.to_screen(u'%s: Downloading video info webpage' % video_id) def report_video_subtitles_download(self, video_id): """Report attempt to download video info webpage.""" - self._downloader.to_screen(u'[youtube] %s: Checking available subtitles' % video_id) + self.to_screen(u'%s: Checking available subtitles' % video_id) def report_video_subtitles_request(self, video_id, sub_lang, format): """Report attempt to download video info webpage.""" - self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format)) + self.to_screen(u'%s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format)) def report_video_subtitles_available(self, video_id, sub_lang_list): """Report available subtitles.""" sub_lang = ",".join(list(sub_lang_list.keys())) - self._downloader.to_screen(u'[youtube] %s: Available subtitles for video: %s' % (video_id, sub_lang)) + self.to_screen(u'%s: Available subtitles for video: %s' % (video_id, sub_lang)) def report_information_extraction(self, video_id): """Report attempt to extract video information.""" - self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id) + self.to_screen(u'%s: Extracting video information' % video_id) def report_unavailable_format(self, video_id, format): """Report extracted video URL.""" - self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format)) + self.to_screen(u'%s: Format %s not available' % (video_id, format)) def report_rtmp_download(self): """Indicate the download will use the RTMP protocol.""" - self._downloader.to_screen(u'[youtube] RTMP download detected') + self.to_screen(u'RTMP download detected') def _get_available_subtitles(self, video_id): self.report_video_subtitles_download(video_id) @@ -253,11 +293,11 @@ class YoutubeIE(InfoExtractor): try: sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None) + return (u'unable to download video subtitles: %s' % compat_str(err), None) sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list) sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list) if not sub_lang_list: - return (u'WARNING: video doesn\'t have subtitles', None) + return (u'video doesn\'t have subtitles', None) return sub_lang_list def _list_available_subtitles(self, video_id): @@ -265,6 +305,10 @@ class YoutubeIE(InfoExtractor): self.report_video_subtitles_available(video_id, sub_lang_list) def _request_subtitle(self, sub_lang, sub_name, video_id, format): + """ + Return tuple: + (error_message, sub_lang, sub) + """ self.report_video_subtitles_request(video_id, sub_lang, format) params = compat_urllib_parse.urlencode({ 'lang': sub_lang, @@ -276,14 +320,20 @@ class YoutubeIE(InfoExtractor): try: sub = compat_urllib_request.urlopen(url).read().decode('utf-8') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None) + return (u'unable to download video subtitles: %s' % compat_str(err), None, None) if not sub: - return (u'WARNING: Did not fetch video subtitles', None) + return (u'Did not fetch video subtitles', None, None) return (None, sub_lang, sub) def _extract_subtitle(self, video_id): + """ + Return a list with a tuple: + [(error_message, sub_lang, sub)] + """ sub_lang_list = self._get_available_subtitles(video_id) sub_format = self._downloader.params.get('subtitlesformat') + if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles + return [(sub_lang_list[0], None, None)] if self._downloader.params.get('subtitleslang', False): sub_lang = self._downloader.params.get('subtitleslang') elif 'en' in sub_lang_list: @@ -291,7 +341,7 @@ class YoutubeIE(InfoExtractor): else: sub_lang = list(sub_lang_list.keys())[0] if not sub_lang in sub_lang_list: - return (u'WARNING: no closed captions found in the specified language "%s"' % sub_lang, None) + return [(u'no closed captions found in the specified language "%s"' % sub_lang, None, None)] subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format) return [subtitle] @@ -299,6 +349,8 @@ class YoutubeIE(InfoExtractor): def _extract_all_subtitles(self, video_id): sub_lang_list = self._get_available_subtitles(video_id) sub_format = self._downloader.params.get('subtitlesformat') + if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles + return [(sub_lang_list[0], None, None)] subtitles = [] for sub_lang in sub_lang_list: subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format) @@ -451,18 +503,14 @@ class YoutubeIE(InfoExtractor): # Get video info self.report_video_info_webpage_download(video_id) for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: - video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' + video_info_url = ('https://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' % (video_id, el_type)) - request = compat_urllib_request.Request(video_info_url) - try: - video_info_webpage_bytes = compat_urllib_request.urlopen(request).read() - video_info_webpage = video_info_webpage_bytes.decode('utf-8', 'ignore') - video_info = compat_parse_qs(video_info_webpage) - if 'token' in video_info: - break - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.report_error(u'unable to download video info webpage: %s' % compat_str(err)) - return + video_info_webpage = self._download_webpage(video_info_url, video_id, + note=False, + errnote='unable to download video info webpage') + video_info = compat_parse_qs(video_info_webpage) + if 'token' in video_info: + break if 'token' not in video_info: if 'reason' in video_info: self._downloader.report_error(u'YouTube said: %s' % video_info['reason'][0]) @@ -532,14 +580,14 @@ class YoutubeIE(InfoExtractor): if video_subtitles: (sub_error, sub_lang, sub) = video_subtitles[0] if sub_error: - self._downloader.trouble(sub_error) + self._downloader.report_error(sub_error) if self._downloader.params.get('allsubtitles', False): video_subtitles = self._extract_all_subtitles(video_id) for video_subtitle in video_subtitles: (sub_error, sub_lang, sub) = video_subtitle if sub_error: - self._downloader.trouble(sub_error) + self._downloader.report_error(sub_error) if self._downloader.params.get('listsubtitles', False): sub_lang_list = self._list_available_subtitles(video_id) @@ -574,8 +622,7 @@ class YoutubeIE(InfoExtractor): format_list = available_formats existing_formats = [x for x in format_list if x in url_map] if len(existing_formats) == 0: - self._downloader.report_error(u'no known formats available for video') - return + raise ExtractorError(u'no known formats available for video') if self._downloader.params.get('listformats', None): self._print_formats(existing_formats) return @@ -595,11 +642,9 @@ class YoutubeIE(InfoExtractor): video_url_list = [(rf, url_map[rf])] break if video_url_list is None: - self._downloader.report_error(u'requested format not available') - return + raise ExtractorError(u'requested format not available') else: - self._downloader.report_error(u'no conn or url_encoded_fmt_stream_map information found in video info') - return + raise ExtractorError(u'no conn or url_encoded_fmt_stream_map information found in video info') results = [] for format_param, video_real_url in video_url_list: @@ -640,19 +685,11 @@ class MetacafeIE(InfoExtractor): def report_disclaimer(self): """Report disclaimer retrieval.""" - self._downloader.to_screen(u'[metacafe] Retrieving disclaimer') - - def report_age_confirmation(self): - """Report attempt to confirm age.""" - self._downloader.to_screen(u'[metacafe] Confirming age') + self.to_screen(u'Retrieving disclaimer') def report_download_webpage(self, video_id): """Report webpage download.""" - self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id) + self.to_screen(u'%s: Downloading webpage' % video_id) def _real_initialize(self): # Retrieve disclaimer @@ -689,17 +726,10 @@ class MetacafeIE(InfoExtractor): # Check if video comes from YouTube mobj2 = re.match(r'^yt-(.*)$', video_id) if mobj2 is not None: - self._downloader.download(['http://www.youtube.com/watch?v=%s' % mobj2.group(1)]) - return + return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')] # Retrieve video webpage to extract further information - request = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id) - 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 retrieve video webpage: %s' % compat_str(err)) - return + webpage = self._download_webpage('http://www.metacafe.com/watch/%s/' % video_id, video_id) # Extract URL, uploader and title from webpage self.report_extraction(video_id) @@ -724,13 +754,13 @@ class MetacafeIE(InfoExtractor): if 'mediaData' not in vardict: self._downloader.report_error(u'unable to extract media URL') return - mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0]) + 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 - mediaURL = mobj.group(1).replace('\\/', '/') + mediaURL = mobj.group('mediaURL').replace('\\/', '/') video_extension = mediaURL[-3:] - video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2)) + video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key')) mobj = re.search(r'(?im)(.*) - Video', webpage) if mobj is None: @@ -764,10 +794,6 @@ class DailymotionIE(InfoExtractor): def __init__(self, downloader=None): InfoExtractor.__init__(self, downloader) - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) - def _real_extract(self, url): # Extract id and simplified title from URL mobj = re.match(self._VALID_URL, url) @@ -795,7 +821,7 @@ class DailymotionIE(InfoExtractor): for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']: if key in flashvars: max_quality = key - self._downloader.to_screen(u'[dailymotion] Using %s' % key) + self.to_screen(u'Using %s' % key) break else: self._downloader.report_error(u'unable to extract video URL') @@ -854,11 +880,7 @@ class PhotobucketIE(InfoExtractor): def report_download_webpage(self, video_id): """Report webpage download.""" - self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id) + self.to_screen(u'%s: Downloading webpage' % video_id) def _real_extract(self, url): # Extract id from URL @@ -923,11 +945,7 @@ class YahooIE(InfoExtractor): def report_download_webpage(self, video_id): """Report webpage download.""" - self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id) + self.to_screen(u'%s: Downloading webpage' % video_id) def _real_extract(self, url, new_video=True): # Extract ID from URL @@ -1063,11 +1081,7 @@ class VimeoIE(InfoExtractor): def report_download_webpage(self, video_id): """Report webpage download.""" - self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id) + self.to_screen(u'%s: Downloading webpage' % video_id) def _real_extract(self, url, new_video=True): # Extract ID from URL @@ -1118,7 +1132,7 @@ class VimeoIE(InfoExtractor): # Extract video description video_description = get_element_by_attribute("itemprop", "description", webpage) if video_description: video_description = clean_html(video_description) - else: video_description = '' + else: video_description = u'' # Extract upload date video_upload_date = None @@ -1149,7 +1163,7 @@ class VimeoIE(InfoExtractor): video_quality = files[quality][0][2] video_codec = files[quality][0][0] video_extension = files[quality][0][1] - self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality)) + 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') @@ -1184,11 +1198,7 @@ class ArteTvIE(InfoExtractor): def report_download_webpage(self, video_id): """Report webpage download.""" - self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id) + self.to_screen(u'%s: Downloading webpage' % video_id) def fetch_webpage(self, url): request = compat_urllib_request.Request(url) @@ -1319,19 +1329,15 @@ class GenericIE(InfoExtractor): def report_download_webpage(self, video_id): """Report webpage download.""" if not self._downloader.params.get('test', False): - self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.') - self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id) + self._downloader.report_warning(u'Falling back on generic information extractor.') + self.to_screen(u'%s: Downloading webpage' % video_id) def report_following_redirect(self, new_url): """Report information extraction.""" self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url) def _test_redirect(self, url): - """Check if it is a redirect, like url shorteners, in case restart chain.""" + """Check if it is a redirect, like url shorteners, in case return the new url.""" class HeadRequest(compat_urllib_request.Request): def get_method(self): return "HEAD" @@ -1382,11 +1388,11 @@ class GenericIE(InfoExtractor): return False self.report_following_redirect(new_url) - self._downloader.download([new_url]) - return True + return new_url def _real_extract(self, url): - if self._test_redirect(url): return + new_url = self._test_redirect(url) + if new_url: return [self.url_result(new_url)] video_id = url.split('/')[-1] try: @@ -1477,11 +1483,9 @@ class YoutubeSearchIE(InfoExtractor): prefix = prefix[8:] query = query.encode('utf-8') if prefix == '': - self._download_n_results(query, 1) - return + return self._get_n_results(query, 1) elif prefix == 'all': - self._download_n_results(query, self._max_youtube_results) - return + self._get_n_results(query, self._max_youtube_results) else: try: n = int(prefix) @@ -1491,14 +1495,12 @@ class YoutubeSearchIE(InfoExtractor): 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 - self._download_n_results(query, n) - return + return self._get_n_results(query, n) except ValueError: # parsing prefix as integer fails - self._download_n_results(query, 1) - return + return self._get_n_results(query, 1) - def _download_n_results(self, query, n): - """Downloads a specified number of results for a query""" + def _get_n_results(self, query, n): + """Get a specified number of results for a query""" video_ids = [] pagenum = 0 @@ -1527,9 +1529,8 @@ class YoutubeSearchIE(InfoExtractor): if len(video_ids) > n: video_ids = video_ids[:n] - for id in video_ids: - self._downloader.download(['http://www.youtube.com/watch?v=%s' % id]) - return + videos = [self.url_result('http://www.youtube.com/watch?v=%s' % id, 'Youtube') for id in video_ids] + return videos class GoogleSearchIE(InfoExtractor): @@ -1547,7 +1548,7 @@ class GoogleSearchIE(InfoExtractor): def report_download_page(self, query, pagenum): """Report attempt to download playlist page with given number.""" query = query.decode(preferredencoding()) - self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum)) + self.to_screen(u'query "%s": Downloading page %s' % (query, pagenum)) def _real_extract(self, query): mobj = re.match(self._VALID_URL, query) @@ -1631,7 +1632,7 @@ class YahooSearchIE(InfoExtractor): def report_download_page(self, query, pagenum): """Report attempt to download playlist page with given number.""" query = query.decode(preferredencoding()) - self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum)) + self.to_screen(u'query "%s": Downloading page %s' % (query, pagenum)) def _real_extract(self, query): mobj = re.match(self._VALID_URL, query) @@ -1761,9 +1762,15 @@ class YoutubePlaylistIE(InfoExtractor): self._downloader.report_error(u'Invalid JSON in API response: ' + compat_str(err)) return - if not 'feed' in response or not 'entry' in response['feed']: + if 'feed' not in response: self._downloader.report_error(u'Got a malformed response from YouTube API') return + 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 ] @@ -1773,37 +1780,31 @@ class YoutubePlaylistIE(InfoExtractor): page_num += 1 videos = [v[1] for v in sorted(videos)] - total = len(videos) - playliststart = self._downloader.params.get('playliststart', 1) - 1 - playlistend = self._downloader.params.get('playlistend', -1) - if playlistend == -1: - videos = videos[playliststart:] - else: - videos = videos[playliststart:playlistend] - - if len(videos) == total: - self._downloader.to_screen(u'[youtube] PL %s: Found %i videos' % (playlist_id, total)) - else: - self._downloader.to_screen(u'[youtube] PL %s: Found %i videos, downloading %i' % (playlist_id, total, len(videos))) - - for video in videos: - self._downloader.download([video]) - return + url_results = [self.url_result(url, 'Youtube') for url in videos] + return [self.playlist_result(url_results, playlist_id, playlist_title)] class YoutubeChannelIE(InfoExtractor): """Information Extractor for YouTube channels.""" - _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$" + _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)" _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en' - _MORE_PAGES_INDICATOR = u"Next \N{RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK}" + _MORE_PAGES_INDICATOR = 'yt-uix-load-more' + _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): + if mobj.group(1) not in ids_in_page: + ids_in_page.append(mobj.group(1)) + return ids_in_page + def _real_extract(self, url): # Extract channel id mobj = re.match(self._VALID_URL, url) @@ -1811,37 +1812,51 @@ class YoutubeChannelIE(InfoExtractor): self._downloader.report_error(u'invalid url: %s' % url) return - # Download channel pages + # Download channel page channel_id = mobj.group(1) video_ids = [] pagenum = 1 - while True: - 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 + 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 - # Extract video identifiers - ids_in_page = [] - for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&', page): - if mobj.group(1) not in ids_in_page: - ids_in_page.append(mobj.group(1)) - video_ids.extend(ids_in_page) + # Extract video identifiers + ids_in_page = self.extract_videos_from_page(page) + video_ids.extend(ids_in_page) - if self._MORE_PAGES_INDICATOR not in page: - break - pagenum = pagenum + 1 + # Download any subsequent channel pages using the json-based channel_ajax query + if self._MORE_PAGES_INDICATOR in 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 = json.loads(page) + + ids_in_page = self.extract_videos_from_page(page['content_html']) + video_ids.extend(ids_in_page) + + if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']: + break self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids))) - for id in video_ids: - self._downloader.download(['http://www.youtube.com/watch?v=%s' % id]) - return + urls = ['http://www.youtube.com/watch?v=%s' % id for id in video_ids] + url_entries = [self.url_result(url, 'Youtube') for url in urls] + return [self.playlist_result(url_entries, channel_id)] class YoutubeUserIE(InfoExtractor): @@ -1911,20 +1926,9 @@ class YoutubeUserIE(InfoExtractor): pagenum += 1 - all_ids_count = len(video_ids) - playliststart = self._downloader.params.get('playliststart', 1) - 1 - playlistend = self._downloader.params.get('playlistend', -1) - - if playlistend == -1: - video_ids = video_ids[playliststart:] - else: - video_ids = video_ids[playliststart:playlistend] - - self._downloader.to_screen(u"[youtube] user %s: Collected %d video ids (downloading %d of them)" % - (username, all_ids_count, len(video_ids))) - - for video_id in video_ids: - self._downloader.download(['http://www.youtube.com/watch?v=%s' % video_id]) + urls = ['http://www.youtube.com/watch?v=%s' % video_id for video_id in video_ids] + url_results = [self.url_result(url, 'Youtube') for url in urls] + return [self.playlist_result(url_results, playlist_title = username)] class BlipTVUserIE(InfoExtractor): @@ -1939,8 +1943,8 @@ class BlipTVUserIE(InfoExtractor): def report_download_page(self, username, pagenum): """Report attempt to download user page.""" - self._downloader.to_screen(u'[%s] user %s: Downloading video ids from page %d' % - (self.IE_NAME, username, pagenum)) + self.to_screen(u'user %s: Downloading video ids from page %d' % + (username, pagenum)) def _real_extract(self, url): # Extract username @@ -2002,20 +2006,9 @@ class BlipTVUserIE(InfoExtractor): pagenum += 1 - all_ids_count = len(video_ids) - playliststart = self._downloader.params.get('playliststart', 1) - 1 - playlistend = self._downloader.params.get('playlistend', -1) - - if playlistend == -1: - video_ids = video_ids[playliststart:] - else: - video_ids = video_ids[playliststart:playlistend] - - self._downloader.to_screen(u"[%s] user %s: Collected %d video ids (downloading %d of them)" % - (self.IE_NAME, username, all_ids_count, len(video_ids))) - - for video_id in video_ids: - self._downloader.download([u'http://blip.tv/'+video_id]) + urls = [u'http://blip.tv/%s' % video_id for video_id in video_ids] + url_entries = [self.url_result(url, 'BlipTV') for url in urls] + return [self.playlist_result(url_entries, playlist_title = username)] class DepositFilesIE(InfoExtractor): @@ -2025,11 +2018,7 @@ class DepositFilesIE(InfoExtractor): def report_download_webpage(self, file_id): """Report webpage download.""" - self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id) - - def report_extraction(self, file_id): - """Report information extraction.""" - self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id) + self.to_screen(u'%s: Downloading webpage' % file_id) def _real_extract(self, url): file_id = url.split('/')[-1] @@ -2088,7 +2077,7 @@ class FacebookIE(InfoExtractor): def report_login(self): """Report attempt to log in.""" - self._downloader.to_screen(u'[%s] Logging in' % self.IE_NAME) + self.to_screen(u'Logging in') def _real_initialize(self): if self._downloader is None: @@ -2144,7 +2133,7 @@ class FacebookIE(InfoExtractor): url = 'https://www.facebook.com/video/video.php?v=%s' % video_id webpage = self._download_webpage(url, video_id) - BEFORE = '[["allowFullScreen","true"],["allowScriptAccess","always"],["salign","tl"],["scale","noscale"],["wmode","opaque"]].forEach(function(param) {swf.addParam(param[0], param[1]);});\n' + BEFORE = '{swf.addParam(param[0], param[1]);});\n' AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});' m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage) if not m: @@ -2152,12 +2141,14 @@ class FacebookIE(InfoExtractor): data = dict(json.loads(m.group(1))) params_raw = compat_urllib_parse.unquote(data['params']) params = json.loads(params_raw) - video_url = params['hd_src'] + video_data = params['video_data'][0] + video_url = video_data.get('hd_src') if not video_url: - video_url = params['sd_src'] + video_url = video_data['sd_src'] if not video_url: raise ExtractorError(u'Cannot find video URL') - video_duration = int(params['video_duration']) + video_duration = int(video_data['video_duration']) + thumbnail = video_data['thumbnail_src'] m = re.search('

([^<]+)

', webpage) if not m: @@ -2170,7 +2161,7 @@ class FacebookIE(InfoExtractor): 'url': video_url, 'ext': 'mp4', 'duration': video_duration, - 'thumbnail': params['thumbnail_src'], + 'thumbnail': thumbnail, } return [info] @@ -2182,13 +2173,9 @@ class BlipTVIE(InfoExtractor): _URL_EXT = r'^.*\.([a-z0-9]+)$' IE_NAME = u'blip.tv' - def report_extraction(self, file_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) - def report_direct_download(self, title): """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title)) + self.to_screen(u'%s: Direct download detected' % title) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -2286,10 +2273,6 @@ class MyVideoIE(InfoExtractor): def __init__(self, downloader=None): InfoExtractor.__init__(self, downloader) - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id) - def _real_extract(self,url): mobj = re.match(self._VALID_URL, url) if mobj is None: @@ -2367,14 +2350,11 @@ class ComedyCentralIE(InfoExtractor): """Receives a URL and returns True if suitable for this IE.""" return re.match(cls._VALID_URL, url, re.VERBOSE) is not None - def report_extraction(self, episode_id): - self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id) - def report_config_download(self, episode_id, media_id): - self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration for %s' % (episode_id, media_id)) + self.to_screen(u'%s: Downloading configuration for %s' % (episode_id, media_id)) def report_index_download(self, episode_id): - self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id) + self.to_screen(u'%s: Downloading show index' % episode_id) def _print_formats(self, formats): print('Available formats:') @@ -2528,11 +2508,8 @@ class EscapistIE(InfoExtractor): _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P[^/]+)/(?P[^/?]+)[/?]?.*$' IE_NAME = u'escapist' - def report_extraction(self, showName): - self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName) - def report_config_download(self, showName): - self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName) + self.to_screen(u'%s: Downloading configuration' % showName) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -2605,11 +2582,7 @@ class CollegeHumorIE(InfoExtractor): def report_manifest(self, video_id): """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Downloading XML manifest' % (self.IE_NAME, video_id)) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + self.to_screen(u'%s: Downloading XML manifest' % video_id) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -2674,10 +2647,6 @@ class XVideosIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' IE_NAME = u'xvideos' - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) if mobj is None: @@ -2744,11 +2713,7 @@ class SoundcloudIE(InfoExtractor): def report_resolve(self, video_id): """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Resolving id' % (self.IE_NAME, video_id)) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Retrieving stream' % (self.IE_NAME, video_id)) + self.to_screen(u'%s: Resolving id' % video_id) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -2817,11 +2782,7 @@ class SoundcloudSetIE(InfoExtractor): def report_resolve(self, video_id): """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Resolving id' % (self.IE_NAME, video_id)) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Retrieving stream' % (self.IE_NAME, video_id)) + self.to_screen(u'%s: Resolving id' % video_id) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -2886,10 +2847,6 @@ class InfoQIE(InfoExtractor): """Information extractor for infoq.com""" _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$' - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) if mobj is None: @@ -2948,11 +2905,7 @@ class MixcloudIE(InfoExtractor): def report_download_json(self, file_id): """Report JSON download.""" - self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME) - - def report_extraction(self, file_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) + self.to_screen(u'Downloading json') def get_urls(self, jsonData, fmt, bitrate='best'): """Get urls from 'audio_formats' section in json""" @@ -3059,11 +3012,7 @@ class StanfordOpenClassroomIE(InfoExtractor): def report_download_webpage(self, objid): """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, objid)) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + self.to_screen(u'%s: Downloading webpage' % objid) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -3169,10 +3118,6 @@ class MTVIE(InfoExtractor): _VALID_URL = r'^(?Phttps?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P[0-9]+)/[^/]+$' IE_NAME = u'mtv' - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) if mobj is None: @@ -3249,11 +3194,7 @@ class YoukuIE(InfoExtractor): def report_download_webpage(self, file_id): """Report webpage download.""" - self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, file_id)) - - def report_extraction(self, file_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) + self.to_screen(u'%s: Downloading webpage' % file_id) def _gen_sid(self): nowTime = int(time.time() * 1000) @@ -3366,11 +3307,7 @@ class XNXXIE(InfoExtractor): def report_webpage(self, video_id): """Report information extraction""" - self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) - - def report_extraction(self, video_id): - """Report information extraction""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + self.to_screen(u'%s: Downloading webpage' % video_id) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -3430,23 +3367,23 @@ class GooglePlusIE(InfoExtractor): def report_extract_entry(self, url): """Report downloading extry""" - self._downloader.to_screen(u'[plus.google] Downloading entry: %s' % url) + self.to_screen(u'Downloading entry: %s' % url) def report_date(self, upload_date): """Report downloading extry""" - self._downloader.to_screen(u'[plus.google] Entry date: %s' % upload_date) + self.to_screen(u'Entry date: %s' % upload_date) def report_uploader(self, uploader): """Report downloading extry""" - self._downloader.to_screen(u'[plus.google] Uploader: %s' % uploader) + self.to_screen(u'Uploader: %s' % uploader) def report_title(self, video_title): """Report downloading extry""" - self._downloader.to_screen(u'[plus.google] Title: %s' % video_title) + self.to_screen(u'Title: %s' % video_title) def report_extract_vid_page(self, video_page): """Report information extraction.""" - self._downloader.to_screen(u'[plus.google] Extracting video page: %s' % video_page) + self.to_screen(u'Extracting video page: %s' % video_page) def _real_extract(self, url): # Extract id from URL @@ -3590,14 +3527,10 @@ class JustinTVIE(InfoExtractor): _JUSTIN_PAGE_LIMIT = 100 IE_NAME = u'justin.tv' - def report_extraction(self, file_id): - """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id)) - def report_download_page(self, channel, offset): """Report attempt to download a single page of videos.""" - self._downloader.to_screen(u'[%s] %s: Downloading video information from %d to %d' % - (self.IE_NAME, channel, offset, offset + self._JUSTIN_PAGE_LIMIT)) + self.to_screen(u'%s: Downloading video information from %d to %d' % + (channel, offset, offset + self._JUSTIN_PAGE_LIMIT)) # Return count of items, list of *valid* items def _parse_page(self, url): @@ -3685,7 +3618,9 @@ class FunnyOrDieIE(InfoExtractor): m = re.search(r"

(?P.*?)</h1>", webpage, flags=re.DOTALL) if not m: - self._downloader.trouble(u'Cannot find video title') + m = re.search(r'<title>(?P<title>[^<]+?)', webpage) + if not m: + self._downloader.trouble(u'Cannot find video title') title = clean_html(m.group('title')) m = re.search(r'\d+)': \{\s*FILENAME: \"(?P[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P[\w:/\.\?=\+-]+)\")?\s*\}," gameID = m.group('gameID') - videourl = 'http://store.steampowered.com/video/%s/' % gameID + videourl = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970' % gameID + self.report_age_confirmation() webpage = self._download_webpage(videourl, gameID) + game_title = re.search(r'

(?P.*?)

', webpage).group('game_title') + + urlRE = r"'movie_(?P\d+)': \{\s*FILENAME: \"(?P[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P[\w:/\.\?=\+-]+)\")?\s*\}," mweb = re.finditer(urlRE, webpage) namesRE = r'(?P.+?)' titles = re.finditer(namesRE, webpage) @@ -3742,7 +3680,7 @@ class SteamIE(InfoExtractor): 'thumbnail': video_thumb } videos.append(info) - return videos + return [self.playlist_result(videos, gameID, game_title)] class UstreamIE(InfoExtractor): _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P\d+)' @@ -3924,7 +3862,7 @@ class YouPornIE(InfoExtractor): if(len(links) == 0): raise ExtractorError(u'ERROR: no known formats available for video') - self._downloader.to_screen(u'[youporn] Links found: %d' % len(links)) + self.to_screen(u'Links found: %d' % len(links)) formats = [] for link in links: @@ -3960,7 +3898,7 @@ class YouPornIE(InfoExtractor): return req_format = self._downloader.params.get('format', None) - self._downloader.to_screen(u'[youporn] Format: %s' % req_format) + self.to_screen(u'Format: %s' % req_format) if req_format is None or req_format == 'best': return [formats[0]] @@ -4119,7 +4057,7 @@ class KeekIE(InfoExtractor): 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'[\S\s]+?

(?P.+?)

', webpage) uploader = clean_html(m.group('uploader')) @@ -4155,8 +4093,8 @@ class TEDIE(InfoExtractor): else : playlist_id=m.group('playlist_id') name=m.group('name') - self._downloader.to_screen(u'[%s] Getting info of playlist %s: "%s"' % (self.IE_NAME,playlist_id,name)) - return self._playlist_videos_info(url,name,playlist_id) + self.to_screen(u'Getting info of playlist %s: "%s"' % (playlist_id,name)) + return [self._playlist_videos_info(url,name,playlist_id)] def _talk_video_link(self,mediaSlug): '''Returns the video link for that mediaSlug''' @@ -4173,12 +4111,17 @@ class TEDIE(InfoExtractor): webpage=self._download_webpage(url, playlist_id, 'Downloading playlist webpage') m_videos=re.finditer(video_RE,webpage,re.VERBOSE) m_names=re.finditer(video_name_RE,webpage) - info=[] + + playlist_RE = r'div class="headline">(\s*?)

(\s*?)(?P.*?)' + m_playlist = re.search(playlist_RE, webpage) + playlist_title = m_playlist.group('playlist_title') + + playlist_entries = [] for m_video, m_name in zip(m_videos,m_names): video_id=m_video.group('video_id') talk_url='http://www.ted.com%s' % m_name.group('talk_url') - info.append(self._talk_info(talk_url,video_id)) - return info + playlist_entries.append(self.url_result(talk_url, 'TED')) + return self.playlist_result(playlist_entries, playlist_id = playlist_id, playlist_title = playlist_title) def _talk_info(self, url, video_id=0): """Return the video for the talk in the url""" @@ -4344,6 +4287,46 @@ class LiveLeakIE(InfoExtractor): return [info] +class ARDIE(InfoExtractor): + _VALID_URL = r'^(?:https?://)?(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P[^/\?]+)(?:\?.*)?' + _TITLE = r'(?P.*)</h1>' + _MEDIA_STREAM = r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)' + + def _real_extract(self, url): + # determine video id from url + m = re.match(self._VALID_URL, url) + + numid = re.search(r'documentId=([0-9]+)', url) + if numid: + video_id = numid.group(1) + else: + video_id = m.group('video_id') + + # determine title and media streams from webpage + html = self._download_webpage(url, video_id) + title = re.search(self._TITLE, html).group('title') + 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 + + # choose default media type and highest quality for now + stream = max([s for s in streams if int(s["media_type"]) == 0], + key=lambda s: int(s["quality"])) + + # there's two possibilities: RTMP stream or HTTP download + info = {'id': video_id, 'title': title, 'ext': 'mp4'} + if stream['rtmp_url']: + self.to_screen(u'RTMP download detected') + assert stream['video_url'].startswith('mp4:') + info["url"] = stream["rtmp_url"] + info["play_path"] = stream['video_url'] + else: + assert stream["video_url"].endswith('.mp4') + info["url"] = stream["video_url"] + return [info] + def gen_extractors(): """ Return a list of an instance of every supported extractor. @@ -4397,5 +4380,10 @@ def gen_extractors(): MySpassIE(), SpiegelIE(), LiveLeakIE(), + ARDIE(), GenericIE() ] + +def get_info_extractor(ie_name): + """Returns the info extractor class with the given ie_name""" + return globals()[ie_name+'IE']