1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-15 10:05:24 +01:00
yt-dlp/youtube_dl/extractor/infoq.py

68 lines
2.1 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
2013-06-23 21:14:19 +02:00
import base64
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
)
class InfoQIE(InfoExtractor):
2014-02-02 12:03:36 +01:00
_VALID_URL = r'https?://(?:www\.)?infoq\.com/[^/]+/(?P<id>[^/]+)$'
2014-04-20 01:01:37 +02:00
2013-06-27 20:27:08 +02:00
_TEST = {
2014-04-21 02:55:35 +02:00
'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things',
'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2',
2014-04-21 02:55:35 +02:00
'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',
2013-06-27 20:27:08 +02:00
},
}
2013-06-23 21:14:19 +02:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2014-02-02 12:03:36 +01:00
video_id = mobj.group('id')
2013-06-23 21:14:19 +02:00
2014-02-02 12:03:36 +01:00
webpage = self._download_webpage(url, video_id)
2013-06-23 21:14:19 +02:00
2014-04-20 01:01:37 +02:00
video_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
video_description = self._html_search_meta('description', webpage, 'description')
2013-06-23 21:14:19 +02:00
2014-04-20 01:10:30 +02:00
# The server URL is hardcoded
2014-04-20 01:01:37 +02:00
video_url = 'rtmpe://video.infoq.com/cfx/st/'
2014-04-20 01:10:30 +02:00
# Extract video URL
encoded_id = self._search_regex(
r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id')
2014-04-20 01:10:30 +02:00
real_id = compat_urllib_parse.unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8'))
playpath = 'mp4:' + real_id
2013-06-23 21:14:19 +02:00
2014-04-20 01:01:37 +02:00
video_filename = playpath.split('/')[-1]
2013-06-23 21:14:19 +02:00
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)
2014-04-21 02:55:35 +02:00
return {
2013-06-23 21:14:19 +02:00
'id': video_id,
'title': video_title,
'description': video_description,
'formats': formats,
2014-04-21 02:55:35 +02:00
}