yt_dlp/extractor/camwithher.py

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