diff options
author | Naglis Jonaitis <njonaitis@gmail.com> | 2015-03-08 13:54:01 +0200 |
---|---|---|
committer | Naglis Jonaitis <njonaitis@gmail.com> | 2015-03-08 13:54:01 +0200 |
commit | 1132eae56d0f693b5dc55529d5cfadf32b32700d (patch) | |
tree | 7bca113d8ae260be26410b11a79ef9ec4a9feceb | |
parent | d34e79492d1d9d9babf85af3737b90c4fe55eb42 (diff) |
[gazeta] Add new extractor (Closes #4222)
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/gazeta.py | 35 |
2 files changed, 36 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index b489d5770..e2475a634 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -175,6 +175,7 @@ from .gameone import ( from .gamespot import GameSpotIE from .gamestar import GameStarIE from .gametrailers import GametrailersIE +from .gazeta import GazetaIE from .gdcvault import GDCVaultIE from .generic import GenericIE from .giantbomb import GiantBombIE diff --git a/youtube_dl/extractor/gazeta.py b/youtube_dl/extractor/gazeta.py new file mode 100644 index 000000000..3f9e58061 --- /dev/null +++ b/youtube_dl/extractor/gazeta.py @@ -0,0 +1,35 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class GazetaIE(InfoExtractor): + _VALID_URL = r'(?P<url>https?://(?:www\.)?gazeta\.ru/(?:(?P<category>[^/]*)/)?video/(?:main/)?(?P<id>[A-Za-z0-9-_]+)\.s?html)' + _TEST = { + 'url': 'http://www.gazeta.ru/video/main/zadaite_vopros_vladislavu_yurevichu.shtml', + 'md5': 'd49c9bdc6e5a7888f27475dc215ee789', + 'info_dict': { + 'id': '205566', + 'ext': 'mp4', + 'title': '«70–80 процентов гражданских в Донецке на грани голода»', + 'description': 'md5:38617526050bd17b234728e7f9620a71', + 'thumbnail': 're:^https?://.*\.jpg', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + + display_id = mobj.group('id') + embed_url = '%s?p=embed' % mobj.group('url') + embed_page = self._download_webpage( + embed_url, display_id, 'Downloading embed page') + + video_id = self._search_regex( + r'<div[^>]*?class="eagleplayer"[^>]*?data-id="([^"]+)"', embed_page, 'video id') + + return self.url_result( + 'eagleplatform:gazeta.media.eagleplatform.com:%s' % video_id, 'EaglePlatform') |