1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-11-30 11:05:35 +08:00
youtube-dl/youtube_dl/extractor/infoq.py
Philipp Hagemeister 1cc79574fc Fix imports and general cleanup
· Import from compat what comes from compat. Yes, some names are available in utils too, but that's an implementation detail.
· Use _match_id consistently whenever possible
· Fix some outdated tests
· Use consistent valid URL (always match the whole protocol, no ^ at start required)
· Use modern test definitions
2014-12-13 12:35:45 +01:00

65 lines
2.1 KiB
Python

from __future__ import unicode_literals
import base64
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
)
class InfoQIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?infoq\.com/[^/]+/(?P<id>[^/]+)$'
_TEST = {
'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things',
'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2',
'info_dict': {
'id': '12-jan-pythonthings',
'ext': 'mp4',
'description': 'Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.',
'title': 'A Few of My Favorite [Python] Things',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
video_description = self._html_search_meta('description', webpage, 'description')
# The server URL is hardcoded
video_url = 'rtmpe://video.infoq.com/cfx/st/'
# Extract video URL
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'))
playpath = 'mp4:' + real_id
video_filename = playpath.split('/')[-1]
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 {
'id': video_id,
'title': video_title,
'description': video_description,
'formats': formats,
}