etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-03 23:25:06 +00:00
Code Issues Projects Releases Wiki Activity

[infoq] Add support for HTTP downloads (Fixes #722)

Browse source
This commit is contained in:
Philipp Hagemeister 2014-04-21 03:21:34 +02:00
parent c0a7c60815
commit edec83a025
1 changed files with 19 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

27
youtube_dl/extractor/infoq.py
View file

@ -13,9 +13,8 @@ class InfoQIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?infoq\.com/[^/]+/(?P<id>[^/]+)$' _VALID_URL = r'https?://(?:www\.)?infoq\.com/[^/]+/(?P<id>[^/]+)$'
_TEST = { _TEST = {
'name': 'InfoQ',
'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things', 'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things',
'md5': 'fcaa3d995e04080dcb9465d86b5eef62', 'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2',
'info_dict': { 'info_dict': {
'id': '12-jan-pythonthings', 'id': '12-jan-pythonthings',
'ext': 'mp4', 'ext': 'mp4',
@ -37,20 +36,32 @@ def _real_extract(self, url):
video_url = 'rtmpe://video.infoq.com/cfx/st/' video_url = 'rtmpe://video.infoq.com/cfx/st/'
# Extract video URL # Extract video URL
encoded_id = self._search_regex(r"jsclassref ?= ?'([^']*)'", webpage, 'encoded id') encoded_id = self._search_regex(
r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id')
real_id = compat_urllib_parse.unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8')) real_id = compat_urllib_parse.unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8'))
playpath = 'mp4:' + real_id playpath = 'mp4:' + real_id
video_filename = playpath.split('/')[-1] video_filename = playpath.split('/')[-1]
video_id, extension = video_filename.split('.') video_id, extension = video_filename.split('.')
http_base = self._search_regex(
r'EXPRESSINSTALL_SWF\s*=\s*"(https?://[^/"]+/)', webpage,
'HTTP base URL')
formats = [{
'format_id': 'rtmp',
'url': video_url,
'ext': extension,
'play_path': playpath,
}, {
'format_id': 'http',
'url': http_base + real_id,
}]
self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,
'title': video_title, 'title': video_title,
'description': video_description, 'description': video_description,
'formats': [{ 'formats': formats,
'url': video_url,
'ext': extension,
'play_path': playpath,
}],
} }