diff options
author | Hannu Lintala <hannu.lintala@gmail.com> | 2015-06-08 05:58:41 +0300 |
---|---|---|
committer | Hannu Lintala <hannu.lintala@gmail.com> | 2015-06-12 01:03:14 +0300 |
commit | 99ac0390f559aa6dd09ffd8a15b9b562fda5f363 (patch) | |
tree | 2f751e449dcd75d53530785e40210c85cff3b72b /youtube_dl | |
parent | 0e805e782bd05951ca3f420cf2a050e2ac3ae846 (diff) |
[fivetv] Add extractor (Closes #5794)
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/fivetv.py | 67 |
2 files changed, 68 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 67eb96057..d10275d03 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -152,6 +152,7 @@ from .fc2 import FC2IE from .firstpost import FirstpostIE from .firsttv import FirstTVIE from .fivemin import FiveMinIE +from .fivetv import FiveTVIE from .fktv import ( FKTVIE, FKTVPosteckeIE, diff --git a/youtube_dl/extractor/fivetv.py b/youtube_dl/extractor/fivetv.py new file mode 100644 index 000000000..e47383b39 --- /dev/null +++ b/youtube_dl/extractor/fivetv.py @@ -0,0 +1,67 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + int_or_none, +) + + +class FiveTVIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?5-tv\.ru/[^/]*/(?P<id>\d+)' + _TESTS = [ + { + 'url': 'http://5-tv.ru/news/96814/', + 'md5': 'bbff554ad415ecf5416a2f48c22d9283', + 'info_dict': { + 'id': '96814', + 'ext': 'mp4', + 'title': 'Россияне выбрали имя для общенациональной платежной системы', + 'description': 'md5:a8aa13e2b7ad36789e9f77a74b6de660', + 'thumbnail': 're:^https?://.*\.jpg$', + 'width': 480, + 'height': 360, + 'duration': 180, + }, + }, + { + 'url': 'http://5-tv.ru/video/1021729/', + 'md5': '299c8b72960efc9990acd2c784dc2296', + 'info_dict': { + 'id': '1021729', + 'ext': 'mp4', + 'title': '3D принтер', + 'description': 'md5:d76c736d29ef7ec5c0cf7d7c65ffcb41', + 'thumbnail': 're:^https?://.*\.jpg$', + 'width': 480, + 'height': 360, + 'duration': 180, + }, + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + video_link = self._search_regex( + r'(<a.*?class="videoplayer">)', webpage, 'video link') + + url = self._search_regex(r'href="([^"]+)"', video_link, 'video url') + width = int_or_none(self._search_regex( + r'width:(\d+)px', video_link, 'width', default=None, fatal=False)) + height = int_or_none(self._search_regex( + r'height:(\d+)px', video_link, 'height', default=None, fatal=False)) + duration = int_or_none(self._og_search_property( + 'video:duration', webpage, 'duration')) + return { + 'id': video_id, + 'url': url, + 'width': width, + 'height': height, + 'title': self._og_search_title(webpage), + 'description': self._og_search_description(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + 'duration': duration, + } |