diff options
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/thvideo.py | 55 |
2 files changed, 56 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 1a6033320..8a5eb8cf1 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -362,6 +362,7 @@ from .thisav import ThisAVIE from .tinypic import TinyPicIE from .tlc import TlcIE, TlcDeIE from .tnaflix import TNAFlixIE +from .thvideo import THVideoIE 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 new file mode 100644 index 000000000..9fa14d3c4 --- /dev/null +++ b/youtube_dl/extractor/thvideo.py @@ -0,0 +1,55 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + unified_strdate +) + + +class THVideoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?thvideo\.tv/v/th(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://thvideo.tv/v/th1987/', + 'md5': 'fa107b1f73817e325e9433505a70db50', + 'info_dict': { + 'id': '1987', + 'ext': 'mp4', + 'title': '【动画】秘封活动记录 ～ The Sealed Esoteric History.分镜稿预览', + 'display_id': 'th1987', + 'thumbnail': 'http://thvideo.tv/uploadfile/2014/0722/20140722013459856.jpg', + 'description': '社团京都幻想剧团的第一个东方二次同人动画作品「秘封活动记录 ～ The Sealed Esoteric History.」 本视频是该动画第一期的分镜草稿...', + 'upload_date': '20140722' + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + # extract download link from mobile player page + webpage_player = self._download_webpage('http://thvideo.tv/mobile.php?cid=%s-0' % video_id, video_id) + video_url = self._html_search_regex(r'<source src="(.*?)" type', webpage_player, 'video url') + + # extract video info from main page + webpage = self._download_webpage(url, video_id) + title = self._og_search_title(webpage) + display_id = 'th%s' % video_id + thumbnail = self._og_search_thumbnail(webpage) + description = self._og_search_description(webpage) + upload_date_raw = self._html_search_regex(r'span itemprop="datePublished" content="(.*?)">', webpage, + 'upload date', fatal=False) + upload_date = unified_strdate(upload_date_raw) + + return { + 'id': video_id, + 'ext': 'mp4', + 'url': video_url, + 'title': title, + 'display_id': display_id, + 'thumbnail': thumbnail, + 'description': description, + 'upload_date': upload_date + }
\ No newline at end of file |