1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
|
from __future__ import unicode_literals
import base64
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
)
class InfoQIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
_TEST = {
"name": "InfoQ",
"url": "http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things",
"file": "12-jan-pythonthings.mp4",
"info_dict": {
"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",
},
"params": {
"skip_download": True,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
webpage = self._download_webpage(url, video_id=url)
self.report_extraction(url)
# Extract video URL
encoded_id = self._search_regex(r"jsclassref ?= ?'([^']*)'", webpage, 'encoded id')
real_id = compat_urllib_parse.unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8'))
video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
# Extract title
video_title = self._search_regex(r'contentTitle = "(.*?)";',
webpage, 'title')
# Extract description
video_description = self._html_search_regex(r'<meta name="description" content="(.*)"(?:\s*/)?>',
webpage, 'description', fatal=False)
video_filename = video_url.split('/')[-1]
video_id, extension = video_filename.split('.')
return {
'id': video_id,
'url': video_url,
'title': video_title,
'ext': extension, # Extension is always(?) mp4, but seems to be flv
'description': video_description,
}
|
