haruhi-dl/youtube_dl/extractor/fivetv.py

89 lines
2.9 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import int_or_none
class FiveTVIE(InfoExtractor):
_VALID_URL = r'''(?x)
http://
(?: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$',
'duration': 180,
},
}, {
'url': 'http://5-tv.ru/video/1021729/',
'info_dict': {
'id': '1021729',
'ext': 'mp4',
'title': '3D принтер',
'description': 'md5:d76c736d29ef7ec5c0cf7d7c65ffcb41',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 180,
},
}, {
'url': 'http://www.5-tv.ru/glavnoe/#itemDetails',
'info_dict': {
'id': 'glavnoe',
'ext': 'mp4',
'title': 'Итоги недели с 8 по 14 июня 2015 года',
'thumbnail': r're:^https?://.*\.jpg$',
},
}, {
'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,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') or mobj.group('path')
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
r'<a[^>]+?href="([^"]+)"[^>]+?class="videoplayer"',
webpage, 'video url')
title = self._og_search_title(webpage, default=None) or self._search_regex(
r'<title>([^<]+)</title>', webpage, 'title')
duration = int_or_none(self._og_search_property(
'video:duration', webpage, 'duration', default=None))
return {
'id': video_id,
'url': video_url,
'title': title,
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'duration': duration,
}