yt-dlc/youtube_dlc/extractor/fivetv.py

92 lines
3.1 KiB
Python
Raw Normal View History

2015-06-08 02:58:41 +00:00
# coding: utf-8
from __future__ import unicode_literals
2015-06-12 11:48:42 +00:00
import re
2015-06-08 02:58:41 +00:00
from .common import InfoExtractor
2015-06-12 11:48:42 +00:00
from ..utils import int_or_none
2015-06-08 02:58:41 +00:00
class FiveTVIE(InfoExtractor):
2015-06-12 11:48:42 +00:00
_VALID_URL = r'''(?x)
https?://
2015-06-12 11:48:42 +00:00
(?:www\.)?5-tv\.ru/
(?:
(?:[^/]+/)+(?P<id>\d+)|
(?P<path>[^/?#]+)(?:[/?#])?
)
'''
_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': r're:^https?://.*\.jpg$',
2015-06-12 11:48:42 +00:00
'duration': 180,
2015-06-08 02:58:41 +00:00
},
2015-06-12 11:48:42 +00:00
}, {
'url': 'http://5-tv.ru/video/1021729/',
'info_dict': {
'id': '1021729',
'ext': 'mp4',
'title': '3D принтер',
'description': 'md5:d76c736d29ef7ec5c0cf7d7c65ffcb41',
'thumbnail': r're:^https?://.*\.jpg$',
2015-06-12 11:48:42 +00:00
'duration': 180,
2015-06-08 02:58:41 +00:00
},
2015-06-12 11:48:42 +00:00
}, {
# redirect to https://www.5-tv.ru/projects/1000095/izvestia-glavnoe/
2015-06-12 11:48:42 +00:00
'url': 'http://www.5-tv.ru/glavnoe/#itemDetails',
'info_dict': {
'id': 'glavnoe',
'ext': 'mp4',
'title': r're:^Итоги недели с \d+ по \d+ \w+ \d{4} года$',
'thumbnail': r're:^https?://.*\.jpg$',
2015-06-12 11:48:42 +00:00
},
'skip': 'redirect to «Известия. Главное» project page',
2015-06-12 11:48:42 +00:00
}, {
'url': 'http://www.5-tv.ru/glavnoe/broadcasts/508645/',
'only_matching': True,
}, {
'url': 'http://5-tv.ru/films/1507502/',
'only_matching': True,
}, {
'url': 'http://5-tv.ru/programs/broadcast/508713/',
'only_matching': True,
}, {
'url': 'http://5-tv.ru/angel/',
'only_matching': True,
}, {
'url': 'http://www.5-tv.ru/schedule/?iframe=true&width=900&height=450',
'only_matching': True,
}]
2015-06-08 02:58:41 +00:00
def _real_extract(self, url):
2015-06-12 11:48:42 +00:00
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') or mobj.group('path')
2015-06-08 02:58:41 +00:00
webpage = self._download_webpage(url, video_id)
2015-06-12 11:48:42 +00:00
video_url = self._search_regex(
[r'<div[^>]+?class="(?:flow)?player[^>]+?data-href="([^"]+)"',
r'<a[^>]+?href="([^"]+)"[^>]+?class="videoplayer"'],
2015-06-12 11:48:42 +00:00
webpage, 'video url')
2015-06-08 02:58:41 +00:00
2015-06-12 11:48:42 +00:00
title = self._og_search_title(webpage, default=None) or self._search_regex(
r'<title>([^<]+)</title>', webpage, 'title')
2015-06-08 02:58:41 +00:00
duration = int_or_none(self._og_search_property(
2015-06-12 11:48:42 +00:00
'video:duration', webpage, 'duration', default=None))
2015-06-08 02:58:41 +00:00
return {
'id': video_id,
2015-06-12 11:48:42 +00:00
'url': video_url,
'title': title,
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
2015-06-08 02:58:41 +00:00
'duration': duration,
}