depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-22 16:57:40 +00:00
Code Issues Releases Wiki Activity

[channel9] Add support for rss links (Closes #9673)

Browse source
This commit is contained in:
Sergey M․ 2016-06-04 04:57:16 +07:00
parent 4d8856d511
commit 762d44c956
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 70 additions and 53 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

53
youtube_dl/extractor/channel9.py
View file

@ -20,10 +20,9 @@ class Channel9IE(InfoExtractor):
''' '''
IE_DESC = 'Channel 9' IE_DESC = 'Channel 9'
IE_NAME = 'channel9' IE_NAME = 'channel9'
_VALID_URL = r'https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+)/?' _VALID_URL = r'https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+?)(?P<rss>/RSS)?/?(?:[?#&]|$)'
_TESTS = [ _TESTS = [{
{
'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002', 'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
'md5': 'bbd75296ba47916b754e73c3a4bbdf10', 'md5': 'bbd75296ba47916b754e73c3a4bbdf10',
'info_dict': { 'info_dict': {
@ -36,10 +35,10 @@ class Channel9IE(InfoExtractor):
'session_code': 'KOS002', 'session_code': 'KOS002',
'session_day': 'Day 1', 'session_day': 'Day 1',
'session_room': 'Arena 1A', 'session_room': 'Arena 1A',
'session_speakers': ['Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug', 'Mads Kristensen'], 'session_speakers': ['Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug',
'Mads Kristensen'],
}, },
}, }, {
{
'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing', 'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing',
'md5': 'b43ee4529d111bc37ba7ee4f34813e68', 'md5': 'b43ee4529d111bc37ba7ee4f34813e68',
'info_dict': { 'info_dict': {
@ -51,8 +50,7 @@ class Channel9IE(InfoExtractor):
'thumbnail': 're:http://.*\.jpg', 'thumbnail': 're:http://.*\.jpg',
'authors': ['Mike Wilmot'], 'authors': ['Mike Wilmot'],
}, },
}, }, {
{
# low quality mp4 is best # low quality mp4 is best
'url': 'https://channel9.msdn.com/Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library', 'url': 'https://channel9.msdn.com/Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
'info_dict': { 'info_dict': {
@ -66,8 +64,20 @@ class Channel9IE(InfoExtractor):
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
} }, {
] 'url': 'https://channel9.msdn.com/Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b/RSS',
'info_dict': {
'id': 'Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b',
'title': 'Channel 9',
},
'playlist_count': 2,
}, {
'url': 'https://channel9.msdn.com/Events/DEVintersection/DEVintersection-2016/RSS',
'only_matching': True,
}, {
'url': 'https://channel9.msdn.com/Events/Speakers/scott-hanselman/RSS?UrlSafeName=scott-hanselman',
'only_matching': True,
}]
_RSS_URL = 'http://channel9.msdn.com/%s/RSS' _RSS_URL = 'http://channel9.msdn.com/%s/RSS'
@ -254,22 +264,30 @@ class Channel9IE(InfoExtractor):
return self.playlist_result(contents) return self.playlist_result(contents)
def _extract_list(self, content_path): def _extract_list(self, video_id, rss_url=None):
rss = self._download_xml(self._RSS_URL % content_path, content_path, 'Downloading RSS') if not rss_url:
rss_url = self._RSS_URL % video_id
rss = self._download_xml(rss_url, video_id, 'Downloading RSS')
entries = [self.url_result(session_url.text, 'Channel9') entries = [self.url_result(session_url.text, 'Channel9')
for session_url in rss.findall('./channel/item/link')] for session_url in rss.findall('./channel/item/link')]
title_text = rss.find('./channel/title').text title_text = rss.find('./channel/title').text
return self.playlist_result(entries, content_path, title_text) return self.playlist_result(entries, video_id, title_text)
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
content_path = mobj.group('contentpath') content_path = mobj.group('contentpath')
rss = mobj.group('rss')
webpage = self._download_webpage(url, content_path, 'Downloading web page') if rss:
return self._extract_list(content_path, url)
page_type_m = re.search(r'<meta name="WT.entryid" content="(?P<pagetype>[^:]+)[^"]+"/>', webpage) webpage = self._download_webpage(
if page_type_m is not None: url, content_path, 'Downloading web page')
page_type = page_type_m.group('pagetype')
page_type = self._search_regex(
r'<meta[^>]+name=(["\'])WT\.entryid\1[^>]+content=(["\'])(?P<pagetype>[^:]+).+?\2',
webpage, 'page type', default=None, group='pagetype')
if page_type:
if page_type == 'Entry': # Any 'item'-like page, may contain downloadable content if page_type == 'Entry': # Any 'item'-like page, may contain downloadable content
return self._extract_entry_item(webpage, content_path) return self._extract_entry_item(webpage, content_path)
elif page_type == 'Session': # Event session page, may contain downloadable content elif page_type == 'Session': # Event session page, may contain downloadable content
@ -278,6 +296,5 @@ class Channel9IE(InfoExtractor):
return self._extract_list(content_path) return self._extract_list(content_path)
else: else:
raise ExtractorError('Unexpected WT.entryid %s' % page_type, expected=True) raise ExtractorError('Unexpected WT.entryid %s' % page_type, expected=True)
else: # Assuming list else: # Assuming list
return self._extract_list(content_path) return self._extract_list(content_path)