[fczenit] Fix extraction and update test

Closes #9359
This commit is contained in:
Yen Chi Hsuan 2016-05-05 17:55:37 +08:00
parent 9da526aae7
commit 4f8c56eb4e
No known key found for this signature in database
GPG Key ID: 3FDDD575826C5C30

View File

@ -1,20 +1,19 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
class FczenitIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?fc-zenit\.ru/video/gl(?P<id>[0-9]+)'
_VALID_URL = r'https?://(?:www\.)?fc-zenit\.ru/video/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://fc-zenit.ru/video/gl6785/',
'md5': '458bacc24549173fe5a5aa29174a5606',
'url': 'http://fc-zenit.ru/video/41044/',
'md5': '0e3fab421b455e970fa1aa3891e57df0',
'info_dict': {
'id': '6785',
'id': '41044',
'ext': 'mp4',
'title': '«Зенит-ТВ»: как Олег Шатов играл против «Урала»',
'title': 'Так пишется история: казанский разгром ЦСКА на «Зенит-ТВ»',
},
}
@ -22,15 +21,23 @@ class FczenitIE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_title = self._html_search_regex(r'<div class=\"photoalbum__title\">([^<]+)', webpage, 'title')
video_title = self._html_search_regex(
r'<[^>]+class=\"photoalbum__title\">([^<]+)', webpage, 'title')
bitrates_raw = self._html_search_regex(r'bitrates:.*\n(.*)\]', webpage, 'video URL')
bitrates = re.findall(r'url:.?\'(.+?)\'.*?bitrate:.?([0-9]{3}?)', bitrates_raw)
video_items = self._parse_json(self._search_regex(
r'arrPath\s*=\s*JSON\.parse\(\'(.+)\'\)', webpage, 'video items'),
video_id)
def merge_dicts(*dicts):
ret = {}
for a_dict in dicts:
ret.update(a_dict)
return ret
formats = [{
'url': furl,
'tbr': tbr,
} for furl, tbr in bitrates]
'url': compat_urlparse.urljoin(url, video_url),
'tbr': int(tbr),
} for tbr, video_url in merge_dicts(*video_items).items()]
self._sort_formats(formats)