[cspan] Use HTTP download (Fixes #2098)

This commit is contained in:
Philipp Hagemeister 2014-01-05 04:30:00 +01:00
parent aff24732b9
commit ca9e792253

View file

@ -1,20 +1,25 @@
from __future__ import unicode_literals
import json
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
compat_urllib_parse, unescapeHTML,
) )
class CSpanIE(InfoExtractor): class CSpanIE(InfoExtractor):
_VALID_URL = r'http://www\.c-spanvideo\.org/program/(.*)' _VALID_URL = r'http://www\.c-spanvideo\.org/program/(.*)'
IE_DESC = 'C-SPAN'
_TEST = { _TEST = {
u'url': u'http://www.c-spanvideo.org/program/HolderonV', 'url': 'http://www.c-spanvideo.org/program/HolderonV',
u'file': u'315139.flv', 'file': '315139.mp4',
u'md5': u'74a623266956f69e4df0068ab6c80fe4', 'md5': '8e44ce11f0f725527daccc453f553eb0',
u'info_dict': { 'info_dict': {
u"title": u"Attorney General Eric Holder on Voting Rights Act Decision" 'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in [Shelby County v. Holder] in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.',
}, },
u'skip': u'Requires rtmpdump'
} }
def _real_extract(self, url): def _real_extract(self, url):
@ -22,30 +27,22 @@ def _real_extract(self, url):
prog_name = mobj.group(1) prog_name = mobj.group(1)
webpage = self._download_webpage(url, prog_name) webpage = self._download_webpage(url, prog_name)
video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id') video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id')
data = compat_urllib_parse.urlencode({'programid': video_id,
'dynamic':'1'})
info_url = 'http://www.c-spanvideo.org/common/services/flashXml.php?' + data
video_info = self._download_webpage(info_url, video_id, u'Downloading video info')
self.report_extraction(video_id) title = self._html_search_regex(
r'<!-- title -->\n\s*<h1[^>]*>(.*?)</h1>', webpage, 'title')
description = self._og_search_description(webpage)
title = self._html_search_regex(r'<string name="title">(.*?)</string>', info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
video_info, 'title') data_json = self._download_webpage(
description = self._html_search_regex(r'<meta (?:property="og:|name=")description" content="(.*?)"', info_url, video_id, 'Downloading video info')
webpage, 'description', data = json.loads(data_json)
flags=re.MULTILINE|re.DOTALL)
url = self._search_regex(r'<string name="URL">(.*?)</string>', url = unescapeHTML(data['video']['files'][0]['path']['#text'])
video_info, 'video url')
url = url.replace('$(protocol)', 'rtmp').replace('$(port)', '443')
path = self._search_regex(r'<string name="path">(.*?)</string>',
video_info, 'rtmp play path')
return {'id': video_id, return {
'id': video_id,
'title': title, 'title': title,
'ext': 'flv',
'url': url, 'url': url,
'play_path': path,
'description': description, 'description': description,
'thumbnail': self._og_search_thumbnail(webpage), 'thumbnail': self._og_search_thumbnail(webpage),
} }