aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/cspan.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/cspan.py')
-rw-r--r--youtube_dl/extractor/cspan.py57
1 files changed, 51 insertions, 6 deletions
diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py
index 2a8eda9ef..795ccd926 100644
--- a/youtube_dl/extractor/cspan.py
+++ b/youtube_dl/extractor/cspan.py
@@ -56,16 +56,61 @@ class CSpanIE(InfoExtractor):
url = unescapeHTML(data['video']['files'][0]['path']['#text'])
- doc = self._download_xml('http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
+ doc = self._download_xml('http://www.c-span.org/common/services/flashXml.php?programid=' + video_id + '&version=2014-01-23',
video_id)
- def find_string(s):
- return find_xpath_attr(doc, './/string', 'name', s).text
+ formats = [
+ {
+ 'url': url,
+ }
+ ]
+
+ def find_string(node, s):
+ return find_xpath_attr(node, './/string', 'name', s).text
+
+ def find_number(node, s):
+ return int(find_xpath_attr(node, './/number', 'name', s).text)
+
+ def find_array(node, s):
+ return find_xpath_attr(node, './/array', 'name', s)
+
+ def process_files(files, url, formats):
+ for file in files:
+ path = find_string(file, 'path')
+ #duration = find_number(file, './number', 'name', 'length')
+ hd = find_number(file, 'hd')
+ formats.append({
+ 'url': url,
+ 'play_path': path,
+ 'ext': 'flv',
+ 'quality': hd,
+ })
+
+ def process_node(node, formats):
+ url = find_xpath_attr(node, './string', 'name', 'url')
+ if url is None:
+ url = find_xpath_attr(node, './string', 'name', 'URL')
+ if url is None:
+ return
+ url = url.text.replace('$(protocol)', 'rtmp').replace('$(port)', '1935')
+ files = find_array(node, 'files')
+ if files is None:
+ return
+ process_files(files, url, formats)
+
+ process_node(doc.find('./media-link'), formats)
+
+ streams = find_array(doc, 'streams')
+ if streams is not None:
+ for stream in streams:
+ if find_string(stream, 'name') != 'vod':
+ continue
+ process_node(stream, formats)
return {
'id': video_id,
- 'title': find_string('title'),
- 'url': url,
+ 'title': find_string(doc, 'title'),
'description': description,
- 'thumbnail': find_string('poster'),
+ 'thumbnail': find_string(doc, 'poster'),
+ 'formats': formats,
}