paradizelost/youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[cspan] Use HTTP download (Fixes #2098)

Browse Source
This commit is contained in:
Philipp Hagemeister 2014-01-05 04:30:00 +01:00
parent aff24732b9
commit ca9e792253
1 changed files with 27 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
youtube_dl/extractor/cspan.py
View File

@ -1,20 +1,25 @@
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
unescapeHTML,
)
class CSpanIE(InfoExtractor):
_VALID_URL = r'http://www\.c-spanvideo\.org/program/(.*)'
IE_DESC = 'C-SPAN'
_TEST = {
u'url': u'http://www.c-spanvideo.org/program/HolderonV',
u'file': u'315139.flv',
u'md5': u'74a623266956f69e4df0068ab6c80fe4',
u'info_dict': {
u"title": u"Attorney General Eric Holder on Voting Rights Act Decision"
'url': 'http://www.c-spanvideo.org/program/HolderonV',
'file': '315139.mp4',
'md5': '8e44ce11f0f725527daccc453f553eb0',
'info_dict': {
'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):
@ -22,30 +27,22 @@ class CSpanIE(InfoExtractor):
prog_name = mobj.group(1)
webpage = self._download_webpage(url, prog_name)
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>',
video_info, 'title')
description = self._html_search_regex(r'<meta (?:property="og:|name=")description" content="(.*?)"',
webpage, 'description',
flags=re.MULTILINE|re.DOTALL)
info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
data_json = self._download_webpage(
info_url, video_id, 'Downloading video info')
data = json.loads(data_json)
url = self._search_regex(r'<string name="URL">(.*?)</string>',
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')
url = unescapeHTML(data['video']['files'][0]['path']['#text'])
return {'id': video_id,
return {
'id': video_id,
'title': title,
'ext': 'flv',
'url': url,
'play_path': path,
'description': description,
'thumbnail': self._og_search_thumbnail(webpage),
}