diff options
author | remitamine <remitamine@gmail.com> | 2015-10-30 13:56:21 +0100 |
---|---|---|
committer | remitamine <remitamine@gmail.com> | 2015-10-30 13:56:21 +0100 |
commit | 957e0db1d2d1d4b2e9fdd1c314b0c46e68ca0cb3 (patch) | |
tree | dc21d518bb8566227d956d29b9ea3dbfa67c3a12 /youtube_dl/extractor | |
parent | 721f5a277ca0012ee72c9d4b3e5550e52a0a596d (diff) | |
download | youtube-dl-957e0db1d2d1d4b2e9fdd1c314b0c46e68ca0cb3.tar.xz |
[baidu] improve info extraction
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/baidu.py | 45 |
1 files changed, 16 insertions, 29 deletions
diff --git a/youtube_dl/extractor/baidu.py b/youtube_dl/extractor/baidu.py index e37ee4440..84fab551b 100644 --- a/youtube_dl/extractor/baidu.py +++ b/youtube_dl/extractor/baidu.py @@ -14,8 +14,8 @@ class BaiduVideoIE(InfoExtractor): 'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6', 'info_dict': { 'id': '1069', - 'title': '中华小当家 TV版 (全52集)', - 'description': 'md5:395a419e41215e531c857bb037bbaf80', + 'title': '中华小当家 TV版国语', + 'description': 'md5:40a9c1b1c7f4e05d642e7bb1c84eeda0', }, 'playlist_count': 52, }, { @@ -25,45 +25,32 @@ class BaiduVideoIE(InfoExtractor): 'title': 're:^奔跑吧兄弟', 'description': 'md5:1bf88bad6d850930f542d51547c089b8', }, - 'playlist_mincount': 3, + 'playlist_mincount': 12, }] + def _call_api(self, path, category, playlist_id): + return self._download_json('http://app.video.baidu.com/%s/?worktype=adnative%s&id=%s' % (path, category, playlist_id), playlist_id) + def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - playlist_id = mobj.group('id') - category = category2 = mobj.group('type') + category, playlist_id = re.match(self._VALID_URL, url).groups() if category == 'show': - category2 = 'tvshow' + category = 'tvshow' + if category == 'tv': + category = 'tvplay' - webpage = self._download_webpage(url, playlist_id) + playlist_detail = self._call_api('xqinfo', category, playlist_id) - playlist_title = self._html_search_regex( - r'title\s*:\s*(["\'])(?P<title>[^\']+)\1', webpage, - 'playlist title', group='title') - playlist_description = self._html_search_regex( - r'<input[^>]+class="j-data-intro"[^>]+value="([^"]+)"/>', webpage, - playlist_id, 'playlist description') + playlist_title = playlist_detail['title'] + playlist_description = playlist_detail.get('intro') - site = self._html_search_regex( - r'filterSite\s*:\s*["\']([^"]*)["\']', webpage, - 'primary provider site') - api_result = self._download_json( - 'http://v.baidu.com/%s_intro/?dtype=%sPlayUrl&id=%s&site=%s' % ( - category, category2, playlist_id, site), - playlist_id, 'Get playlist links') + episodes_detail = self._call_api('xqsingle', category, playlist_id) entries = [] - for episode in api_result[0]['episodes']: + for episode in episodes_detail['videos']: episode_id = '%s_%s' % (playlist_id, episode['episode']) - redirect_page = self._download_webpage( - compat_urlparse.urljoin(url, episode['url']), episode_id, - note='Download Baidu redirect page') - real_url = self._html_search_regex( - r'location\.replace\("([^"]+)"\)', redirect_page, 'real URL') - entries.append(self.url_result( - real_url, video_title=episode['single_title'])) + episode['url'], video_title=episode['title'])) return self.playlist_result( entries, playlist_id, playlist_title, playlist_description) |