X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/a070911bf98c751e4425008f1335cc57c86d30fc..ed6eef637d5115dea4adc4e40f030f0688f29c37:/youtube_dl/extractor/tudou.py diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py index c89de5b..2aae55e 100644 --- a/youtube_dl/extractor/tudou.py +++ b/youtube_dl/extractor/tudou.py @@ -2,14 +2,20 @@ from __future__ import unicode_literals -import re -import json - from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + ExtractorError, + int_or_none, + InAdvancePagedList, + float_or_none, + unescapeHTML, +) class TudouIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:listplay|programs(?:/view)?|albumplay)/.*?/(?P[^/?#]+?)(?:\.html)?/?(?:$|[?#])' + IE_NAME = 'tudou' + _VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:(?:programs|wlplay)/view|(?:listplay|albumplay)/[\w-]{11})/(?P[\w-]{11})' _TESTS = [{ 'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html', 'md5': '140a49ed444bd22f93330985d8475fcb', @@ -17,7 +23,12 @@ class TudouIE(InfoExtractor): 'id': '159448201', 'ext': 'f4v', 'title': '卡马乔国足开大脚长传冲吊集锦', - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1372113489000, + 'description': '卡马乔卡家军，开大脚先进战术不完全集锦！', + 'duration': 289.04, + 'view_count': int, + 'filesize': int, } }, { 'url': 'http://www.tudou.com/programs/view/ajX3gyhL0pc/', @@ -25,63 +36,146 @@ class TudouIE(InfoExtractor): 'id': '117049447', 'ext': 'f4v', 'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012', - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1349207518000, + 'description': 'md5:294612423894260f2dcd5c6c04fe248b', + 'duration': 5478.33, + 'view_count': int, + 'filesize': int, } }] - def _url_for_id(self, id, quality=None): - info_url = "http://v2.tudou.com/f?id=" + str(id) + _PLAYER_URL = 'http://js.tudouui.com/bin/lingtong/PortalPlayer_177.swf' + + # Translated from tudou/tools/TVCHelper.as in PortalPlayer_193.swf + # 0001, 0002 and 4001 are not included as they indicate temporary issues + TVC_ERRORS = { + '0003': 'The video is deleted or does not exist', + '1001': 'This video is unavailable due to licensing issues', + '1002': 'This video is unavailable as it\'s under review', + '1003': 'This video is unavailable as it\'s under review', + '3001': 'Password required', + '5001': 'This video is available in Mainland China only due to licensing issues', + '7001': 'This video is unavailable', + '8001': 'This video is unavailable due to licensing issues', + } + + def _url_for_id(self, video_id, quality=None): + info_url = 'http://v2.tudou.com/f?id=' + compat_str(video_id) if quality: info_url += '&hd' + quality - webpage = self._download_webpage(info_url, id, "Opening the info webpage") - final_url = self._html_search_regex('>(.+?)', webpage, 'video url') + xml_data = self._download_xml(info_url, video_id, 'Opening the info XML page') + error = xml_data.attrib.get('error') + if error is not None: + raise ExtractorError('Tudou said: %s' % error, expected=True) + final_url = xml_data.text return final_url def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - m = re.search(r'vcode:\s*[\'"](.+?)[\'"]', webpage) - if m and m.group(1): - return { - '_type': 'url', - 'url': 'youku:' + m.group(1), - 'ie_key': 'Youku' - } - - title = self._search_regex( - r",kw:\s*['\"](.+?)[\"']", webpage, 'title') - thumbnail_url = self._search_regex( - r",pic:\s*[\"'](.+?)[\"']", webpage, 'thumbnail URL', fatal=False) - - segs_json = self._search_regex(r'segs: \'(.*)\'', webpage, 'segments') - segments = json.loads(segs_json) + item_data = self._download_json( + 'http://www.tudou.com/tvp/getItemInfo.action?ic=%s' % video_id, video_id) + + youku_vcode = item_data.get('vcode') + if youku_vcode: + return self.url_result('youku:' + youku_vcode, ie='Youku') + + if not item_data.get('itemSegs'): + tvc_code = item_data.get('tvcCode') + if tvc_code: + err_msg = self.TVC_ERRORS.get(tvc_code) + if err_msg: + raise ExtractorError('Tudou said: %s' % err_msg, expected=True) + raise ExtractorError('Unexpected error %s returned from Tudou' % tvc_code) + raise ExtractorError('Unxpected error returned from Tudou') + + title = unescapeHTML(item_data['kw']) + description = item_data.get('desc') + thumbnail_url = item_data.get('pic') + view_count = int_or_none(item_data.get('playTimes')) + timestamp = int_or_none(item_data.get('pt')) + + segments = self._parse_json(item_data['itemSegs'], video_id) # It looks like the keys are the arguments that have to be passed as # the hd field in the request url, we pick the higher # Also, filter non-number qualities (see issue #3643). quality = sorted(filter(lambda k: k.isdigit(), segments.keys()), key=lambda k: int(k))[-1] parts = segments[quality] - result = [] len_parts = len(parts) if len_parts > 1: self.to_screen('%s: found %s parts' % (video_id, len_parts)) - for part in parts: + + def part_func(partnum): + part = parts[partnum] part_id = part['k'] final_url = self._url_for_id(part_id, quality) ext = (final_url.split('?')[0]).split('.')[-1] - part_info = { + return [{ 'id': '%s' % part_id, 'url': final_url, 'ext': ext, 'title': title, 'thumbnail': thumbnail_url, - } - result.append(part_info) + 'description': description, + 'view_count': view_count, + 'timestamp': timestamp, + 'duration': float_or_none(part.get('seconds'), 1000), + 'filesize': int_or_none(part.get('size')), + 'http_headers': { + 'Referer': self._PLAYER_URL, + }, + }] + + entries = InAdvancePagedList(part_func, len_parts, 1) return { '_type': 'multi_video', - 'entries': result, + 'entries': entries, 'id': video_id, 'title': title, } + + +class TudouPlaylistIE(InfoExtractor): + IE_NAME = 'tudou:playlist' + _VALID_URL = r'https?://(?:www\.)?tudou\.com/listplay/(?P[\w-]{11})\.html' + _TESTS = [{ + 'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo.html', + 'info_dict': { + 'id': 'zzdE77v6Mmo', + }, + 'playlist_mincount': 209, + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + playlist_data = self._download_json( + 'http://www.tudou.com/tvp/plist.action?lcode=%s' % playlist_id, playlist_id) + entries = [self.url_result( + 'http://www.tudou.com/programs/view/%s' % item['icode'], + 'Tudou', item['icode'], + item['kw']) for item in playlist_data['items']] + return self.playlist_result(entries, playlist_id) + + +class TudouAlbumIE(InfoExtractor): + IE_NAME = 'tudou:album' + _VALID_URL = r'https?://(?:www\.)?tudou\.com/album(?:cover|play)/(?P[\w-]{11})' + _TESTS = [{ + 'url': 'http://www.tudou.com/albumplay/v5qckFJvNJg.html', + 'info_dict': { + 'id': 'v5qckFJvNJg', + }, + 'playlist_mincount': 45, + }] + + def _real_extract(self, url): + album_id = self._match_id(url) + album_data = self._download_json( + 'http://www.tudou.com/tvp/alist.action?acode=%s' % album_id, album_id) + entries = [self.url_result( + 'http://www.tudou.com/programs/view/%s' % item['icode'], + 'Tudou', item['icode'], + item['kw']) for item in album_data['items']] + return self.playlist_result(entries, album_id)