diff options
| author | Philipp Hagemeister <phihag@phihag.de> | 2014-09-29 00:36:55 +0200 | 
|---|---|---|
| committer | Philipp Hagemeister <phihag@phihag.de> | 2014-09-29 00:36:55 +0200 | 
| commit | 457ac58cc72a0b7161a0369a8f282f38ff0f2f93 (patch) | |
| tree | 600fa2c4b244182c257b467ae0b6933859b9934f | |
| parent | 9c44d2429b90dece734df778c63b04c15e91c1ca (diff) | |
| parent | 67077b182b698ac56cec9525a2669d5cee394226 (diff) | |
Merge remote-tracking branch 'diffycat/thvideo-update'
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 5 | ||||
| -rw-r--r-- | youtube_dl/extractor/thvideo.py | 24 | 
2 files changed, 28 insertions, 1 deletions
| diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 86bff185b..89a9d8106 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -371,7 +371,10 @@ from .thisav import ThisAVIE  from .tinypic import TinyPicIE  from .tlc import TlcIE, TlcDeIE  from .tnaflix import TNAFlixIE -from .thvideo import THVideoIE +from .thvideo import ( +    THVideoIE, +    THVideoPlaylistIE +)  from .toutv import TouTvIE  from .toypics import ToypicsUserIE, ToypicsIE  from .traileraddict import TrailerAddictIE diff --git a/youtube_dl/extractor/thvideo.py b/youtube_dl/extractor/thvideo.py index 607e947bb..0ae20ea30 100644 --- a/youtube_dl/extractor/thvideo.py +++ b/youtube_dl/extractor/thvideo.py @@ -57,3 +57,27 @@ class THVideoIE(InfoExtractor):              'description': description,              'upload_date': upload_date          } + + +class THVideoPlaylistIE(InfoExtractor): +    _VALID_URL = r'http?://(?:www\.)?thvideo\.tv/mylist(?P<id>[0-9]+)' +    _TEST = { +        'url': 'http://thvideo.tv/mylist2', +        'info_dict': { +            'id': '2', +            'title': '幻想万華鏡', +        }, +        'playlist_mincount': 23, +    } + +    def _real_extract(self, url): +        webpage = self._download_webpage(url, 'playlist') +        mobj = re.match(self._VALID_URL, url) +        list_id = mobj.group('id') +        list_title = self._html_search_regex(r'<h1 class="show_title">(.*?)<b id', webpage, 'playlist title') + +        entries = [ +            self.url_result('http://thvideo.tv/v/th' + id, 'THVideo') +            for id in re.findall(r'<dd><a href="http://thvideo.tv/v/th(\d+)/" target=', webpage)] + +        return self.playlist_result(entries, list_id, list_title)
\ No newline at end of file | 
