depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-26 12:11:52 +00:00
Code Issues Releases Wiki Activity

Merge remote-tracking branch 'dstftw/channel9'

Browse source
This commit is contained in:
Philipp Hagemeister 2014-01-28 21:46:42 +01:00
commit 6490306017
1 changed files with 35 additions and 35 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

68
youtube_dl/extractor/channel9.py
View file

@ -1,4 +1,4 @@
# encoding: utf-8 from __future__ import unicode_literals
import re import re
@ -13,36 +13,36 @@ class Channel9IE(InfoExtractor):
meta Search.PageType from web page HTML rather than URL itself, as it is meta Search.PageType from web page HTML rather than URL itself, as it is
not always possible to do. not always possible to do.
''' '''
IE_DESC = u'Channel 9' IE_DESC = 'Channel 9'
IE_NAME = u'channel9' IE_NAME = 'channel9'
_VALID_URL = r'^https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+)/?' _VALID_URL = r'^https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+)/?'
_TESTS = [ _TESTS = [
{ {
u'url': u'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002', 'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
u'file': u'Events_TechEd_Australia_2013_KOS002.mp4', 'file': 'Events_TechEd_Australia_2013_KOS002.mp4',
u'md5': u'bbd75296ba47916b754e73c3a4bbdf10', 'md5': 'bbd75296ba47916b754e73c3a4bbdf10',
u'info_dict': { 'info_dict': {
u'title': u'Developer Kick-Off Session: Stuff We Love', 'title': 'Developer Kick-Off Session: Stuff We Love',
u'description': u'md5:c08d72240b7c87fcecafe2692f80e35f', 'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
u'duration': 4576, 'duration': 4576,
u'thumbnail': u'http://media.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg', 'thumbnail': 'http://media.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg',
u'session_code': u'KOS002', 'session_code': 'KOS002',
u'session_day': u'Day 1', 'session_day': 'Day 1',
u'session_room': u'Arena 1A', 'session_room': 'Arena 1A',
u'session_speakers': [ u'Ed Blankenship', u'Andrew Coates', u'Brady Gaster', u'Patrick Klug', u'Mads Kristensen' ], 'session_speakers': [ 'Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug', 'Mads Kristensen' ],
}, },
}, },
{ {
u'url': u'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',
u'file': u'posts_Self-service-BI-with-Power-BI-nuclear-testing.mp4', 'file': 'posts_Self-service-BI-with-Power-BI-nuclear-testing.mp4',
u'md5': u'b43ee4529d111bc37ba7ee4f34813e68', 'md5': 'b43ee4529d111bc37ba7ee4f34813e68',
u'info_dict': { 'info_dict': {
u'title': u'Self-service BI with Power BI - nuclear testing', 'title': 'Self-service BI with Power BI - nuclear testing',
u'description': u'md5:d1e6ecaafa7fb52a2cacdf9599829f5b', 'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
u'duration': 1540, 'duration': 1540,
u'thumbnail': u'http://media.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg', 'thumbnail': 'http://media.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg',
u'authors': [ u'Mike Wilmot' ], 'authors': [ 'Mike Wilmot' ],
}, },
} }
] ]
@ -60,7 +60,7 @@ class Channel9IE(InfoExtractor):
return 0 return 0
units = m.group('units') units = m.group('units')
try: try:
exponent = [u'B', u'KB', u'MB', u'GB', u'TB', u'PB', u'EB', u'ZB', u'YB'].index(units.upper()) exponent = ['B', 'KB', 'MB', 'GB', 'TB', 'PB', 'EB', 'ZB', 'YB'].index(units.upper())
except ValueError: except ValueError:
return 0 return 0
size = float(m.group('size')) size = float(m.group('size'))
@ -80,7 +80,7 @@ class Channel9IE(InfoExtractor):
'url': x.group('url'), 'url': x.group('url'),
'format_id': x.group('quality'), 'format_id': x.group('quality'),
'format_note': x.group('note'), 'format_note': x.group('note'),
'format': u'%s (%s)' % (x.group('quality'), x.group('note')), 'format': '%s (%s)' % (x.group('quality'), x.group('note')),
'filesize': self._restore_bytes(x.group('filesize')), # File size is approximate 'filesize': self._restore_bytes(x.group('filesize')), # File size is approximate
'preference': self._known_formats.index(x.group('quality')), 'preference': self._known_formats.index(x.group('quality')),
'vcodec': 'none' if x.group('note') == 'Audio only' else None, 'vcodec': 'none' if x.group('note') == 'Audio only' else None,
@ -91,10 +91,10 @@ class Channel9IE(InfoExtractor):
return formats return formats
def _extract_title(self, html): def _extract_title(self, html):
title = self._html_search_meta(u'title', html, u'title') title = self._html_search_meta('title', html, 'title')
if title is None: if title is None:
title = self._og_search_title(html) title = self._og_search_title(html)
TITLE_SUFFIX = u' (Channel 9)' TITLE_SUFFIX = ' (Channel 9)'
if title is not None and title.endswith(TITLE_SUFFIX): if title is not None and title.endswith(TITLE_SUFFIX):
title = title[:-len(TITLE_SUFFIX)] title = title[:-len(TITLE_SUFFIX)]
return title return title
@ -110,7 +110,7 @@ class Channel9IE(InfoExtractor):
m = re.search(DESCRIPTION_REGEX, html) m = re.search(DESCRIPTION_REGEX, html)
if m is not None: if m is not None:
return m.group('description') return m.group('description')
return self._html_search_meta(u'description', html, u'description') return self._html_search_meta('description', html, 'description')
def _extract_duration(self, html): def _extract_duration(self, html):
m = re.search(r'data-video_duration="(?P<hours>\d{2}):(?P<minutes>\d{2}):(?P<seconds>\d{2})"', html) m = re.search(r'data-video_duration="(?P<hours>\d{2}):(?P<minutes>\d{2}):(?P<seconds>\d{2})"', html)
@ -172,7 +172,7 @@ class Channel9IE(InfoExtractor):
# Nothing to download # Nothing to download
if len(formats) == 0 and slides is None and zip_ is None: if len(formats) == 0 and slides is None and zip_ is None:
self._downloader.report_warning(u'None of recording, slides or zip are available for %s' % content_path) self._downloader.report_warning('None of recording, slides or zip are available for %s' % content_path)
return return
# Extract meta # Extract meta
@ -244,7 +244,7 @@ class Channel9IE(InfoExtractor):
return contents return contents
def _extract_list(self, content_path): def _extract_list(self, content_path):
rss = self._download_xml(self._RSS_URL % content_path, content_path, u'Downloading RSS') rss = self._download_xml(self._RSS_URL % content_path, content_path, '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
@ -254,11 +254,11 @@ class Channel9IE(InfoExtractor):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
content_path = mobj.group('contentpath') content_path = mobj.group('contentpath')
webpage = self._download_webpage(url, content_path, u'Downloading web page') webpage = self._download_webpage(url, content_path, 'Downloading web page')
page_type_m = re.search(r'<meta name="Search.PageType" content="(?P<pagetype>[^"]+)"/>', webpage) page_type_m = re.search(r'<meta name="Search.PageType" content="(?P<pagetype>[^"]+)"/>', webpage)
if page_type_m is None: if page_type_m is None:
raise ExtractorError(u'Search.PageType not found, don\'t know how to process this page', expected=True) raise ExtractorError('Search.PageType not found, don\'t know how to process this page', expected=True)
page_type = page_type_m.group('pagetype') page_type = page_type_m.group('pagetype')
if page_type == 'List': # List page, may contain list of 'item'-like objects if page_type == 'List': # List page, may contain list of 'item'-like objects
@ -268,4 +268,4 @@ class Channel9IE(InfoExtractor):
elif page_type == 'Session': # Event session page, may contain downloadable content elif page_type == 'Session': # Event session page, may contain downloadable content
return self._extract_session(webpage, content_path) return self._extract_session(webpage, content_path)
else: else:
raise ExtractorError(u'Unexpected Search.PageType %s' % page_type, expected=True) raise ExtractorError('Unexpected Search.PageType %s' % page_type, expected=True)