diff options
author | Sergey M․ <dstftw@gmail.com> | 2015-04-01 22:02:55 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2015-04-01 22:02:55 +0600 |
commit | 55cde6ef3c046dfd5f6ef84b908d38ee4375cf08 (patch) | |
tree | 419ec7dc719a81d1ba5b74ba615e87cf8148b851 | |
parent | 69c3af567d852a0be7bb39b1ca7348e0d5712ec3 (diff) |
[varzesh3] Simplify
-rw-r--r-- | youtube_dl/extractor/varzesh3.py | 43 |
1 files changed, 20 insertions, 23 deletions
diff --git a/youtube_dl/extractor/varzesh3.py b/youtube_dl/extractor/varzesh3.py index eb49586cc..9369abaf8 100644 --- a/youtube_dl/extractor/varzesh3.py +++ b/youtube_dl/extractor/varzesh3.py @@ -1,48 +1,45 @@ # coding: utf-8 from __future__ import unicode_literals + from .common import InfoExtractor -from ..utils import ( - ExtractorError, -) -import re class Varzesh3IE(InfoExtractor): - _VALID_URL = r'(?P<url>(https?://(?:www\.)?video\.varzesh3\.com)/(?P<id>.+))' - _TEST ={ + _VALID_URL = r'https?://(?:www\.)?video\.varzesh3\.com/(?:[^/]+/)+(?P<id>[^/]+)/?' + _TEST = { 'url': 'http://video.varzesh3.com/germany/bundesliga/5-%D9%88%D8%A7%DA%A9%D9%86%D8%B4-%D8%A8%D8%B1%D8%AA%D8%B1-%D8%AF%D8%B1%D9%88%D8%A7%D8%B2%D9%87%E2%80%8C%D8%A8%D8%A7%D9%86%D8%A7%D9%86%D8%9B%D9%87%D9%81%D8%AA%D9%87-26-%D8%A8%D9%88%D9%86%D8%AF%D8%B3/', 'md5': '2a933874cb7dce4366075281eb49e855', 'info_dict': { - 'url': 'http://dl1.video.varzesh3.com/video/clip94/1/video/namayeshi/saves_week26.mp4', 'id': '76337', 'ext': 'mp4', 'title': '۵ واکنش برتر دروازهبانان؛هفته ۲۶ بوندسلیگا', - 'thumbnail': 'http://video.varzesh3.com/wp-content/uploads/230315_saves_week26.jpg', 'description': 'فصل ۲۰۱۵-۲۰۱۴', + 'thumbnail': 're:^https?://.*\.jpg$', } } def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + video_url = self._search_regex( + r'<source[^>]+src="([^"]+)"', webpage, 'video url') - if not 'shortlink' in webpage: - raise ExtractorError('URL has no videos or there is a problem.') + title = self._og_search_title(webpage) + description = self._html_search_regex( + r'(?s)<div class="matn">(.+?)</div>', + webpage, 'description', fatal=False) + thumbnail = self._og_search_thumbnail(webpage) - title = self._html_search_regex(r'meta[^>]+property="og:title"[^>]+content="([^"]+)"', webpage, 'title') - video_link = self._html_search_regex(r'source[^>]+src="([^"]+)"', webpage, 'video_link') - vid_id = self._html_search_regex(r"link[^>]+rel='canonical'[^>]+href='\/\?p=([^']+)'\/>", webpage, 'vid_id') - try: - description = self._html_search_regex(r'<div class="matn">(.*?)</div>', webpage, 'description', flags=re.DOTALL) - except: - description = title - thumbnail = self._html_search_regex(r'link[^>]+rel="image_src"[^>]+href="([^"]+)"', webpage, 'thumbnail') + video_id = self._search_regex( + r"<link[^>]+rel='(?:canonical|shortlink)'[^>]+href='/\?p=([^']+)'", + webpage, display_id, default=display_id) return { - 'url': video_link, - 'id': vid_id, + 'url': video_url, + 'id': video_id, 'title': title, - 'ext': video_link.split(".")[-1], 'description': description, 'thumbnail': thumbnail, } |