aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dl/extractor/cspan.py
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-06-26 17:55:54 +0200
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-06-26 17:55:54 +0200
commitaa0c87391c7b84cde2fa8e307ffe5329e8ed3e5b (patch)
treeaedfa705ca6cab8385a1fd06664604b69f2cc942 /youtube_dl/extractor/cspan.py
parent2e3252801219dc82c379ba00a30c629039b06a24 (diff)
downloadyoutube-dl-aa0c87391c7b84cde2fa8e307ffe5329e8ed3e5b.zip
youtube-dl-aa0c87391c7b84cde2fa8e307ffe5329e8ed3e5b.tar.gz
youtube-dl-aa0c87391c7b84cde2fa8e307ffe5329e8ed3e5b.tar.bz2
Add CSpanIE (closes #312)
Diffstat (limited to 'youtube_dl/extractor/cspan.py')
-rw-r--r--youtube_dl/extractor/cspan.py44
1 files changed, 44 insertions, 0 deletions
diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py
new file mode 100644
index 0000000..2246515
--- /dev/null
+++ b/youtube_dl/extractor/cspan.py
@@ -0,0 +1,44 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_parse,
+)
+
+class CSpanIE(InfoExtractor):
+ _VALID_URL = r'http://www.c-spanvideo.org/program/(.*)'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ 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'<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)
+ thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.*?)"',
+ webpage, 'thumbnail')
+
+ 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')
+
+ return {'id': video_id,
+ 'title': title,
+ 'ext': 'flv',
+ 'url': url,
+ 'play_path': path,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ }