]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/camwithher.py
Update upstream source from tag 'upstream/2019.09.28'
[youtubedl] / youtube_dl / extractor / camwithher.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import (
7 int_or_none,
8 parse_duration,
9 unified_strdate,
10 )
11
12
13 class CamWithHerIE(InfoExtractor):
14 _VALID_URL = r'https?://(?:www\.)?camwithher\.tv/view_video\.php\?.*\bviewkey=(?P<id>\w+)'
15
16 _TESTS = [{
17 'url': 'http://camwithher.tv/view_video.php?viewkey=6e9a24e2c0e842e1f177&page=&viewtype=&category=',
18 'info_dict': {
19 'id': '5644',
20 'ext': 'flv',
21 'title': 'Periscope Tease',
22 'description': 'In the clouds teasing on periscope to my favorite song',
23 'duration': 240,
24 'view_count': int,
25 'comment_count': int,
26 'uploader': 'MileenaK',
27 'upload_date': '20160322',
28 'age_limit': 18,
29 },
30 'params': {
31 'skip_download': True,
32 }
33 }, {
34 'url': 'http://camwithher.tv/view_video.php?viewkey=6dfd8b7c97531a459937',
35 'only_matching': True,
36 }, {
37 'url': 'http://camwithher.tv/view_video.php?page=&viewkey=6e9a24e2c0e842e1f177&viewtype=&category=',
38 'only_matching': True,
39 }, {
40 'url': 'http://camwithher.tv/view_video.php?viewkey=b6c3b5bea9515d1a1fc4&page=&viewtype=&category=mv',
41 'only_matching': True,
42 }]
43
44 def _real_extract(self, url):
45 video_id = self._match_id(url)
46
47 webpage = self._download_webpage(url, video_id)
48
49 flv_id = self._html_search_regex(
50 r'<a[^>]+href=["\']/download/\?v=(\d+)', webpage, 'video id')
51
52 # Video URL construction algorithm is reverse-engineered from cwhplayer.swf
53 rtmp_url = 'rtmp://camwithher.tv/clipshare/%s' % (
54 ('mp4:%s.mp4' % flv_id) if int(flv_id) > 2010 else flv_id)
55
56 title = self._html_search_regex(
57 r'<div[^>]+style="float:left"[^>]*>\s*<h2>(.+?)</h2>', webpage, 'title')
58 description = self._html_search_regex(
59 r'>Description:</span>(.+?)</div>', webpage, 'description', default=None)
60
61 runtime = self._search_regex(
62 r'Runtime\s*:\s*(.+?) \|', webpage, 'duration', default=None)
63 if runtime:
64 runtime = re.sub(r'[\s-]', '', runtime)
65 duration = parse_duration(runtime)
66 view_count = int_or_none(self._search_regex(
67 r'Views\s*:\s*(\d+)', webpage, 'view count', default=None))
68 comment_count = int_or_none(self._search_regex(
69 r'Comments\s*:\s*(\d+)', webpage, 'comment count', default=None))
70
71 uploader = self._search_regex(
72 r'Added by\s*:\s*<a[^>]+>([^<]+)</a>', webpage, 'uploader', default=None)
73 upload_date = unified_strdate(self._search_regex(
74 r'Added on\s*:\s*([\d-]+)', webpage, 'upload date', default=None))
75
76 return {
77 'id': flv_id,
78 'url': rtmp_url,
79 'ext': 'flv',
80 'no_resume': True,
81 'title': title,
82 'description': description,
83 'duration': duration,
84 'view_count': view_count,
85 'comment_count': comment_count,
86 'uploader': uploader,
87 'upload_date': upload_date,
88 'age_limit': 18
89 }