yt_dlp/extractor/vidlii.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..networking import HEADRequest
   5 from ..utils import (
   6     format_field,
   7     float_or_none,
   8     get_element_by_id,
   9     int_or_none,
  10     str_to_int,
  11     strip_or_none,
  12     unified_strdate,
  13     urljoin,
  14 )
  15
  16
  17 class VidLiiIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?:www\.)?vidlii\.com/(?:watch|embed)\?.*?\bv=(?P<id>[0-9A-Za-z_-]{11})'
  19     _TESTS = [{
  20         'url': 'https://www.vidlii.com/watch?v=tJluaH4BJ3v',
  21         'md5': '9bf7d1e005dfa909b6efb0a1ff5175e2',
  22         'info_dict': {
  23             'id': 'tJluaH4BJ3v',
  24             'ext': 'mp4',
  25             'title': 'Vidlii is against me',
  26             'description': 'md5:fa3f119287a2bfb922623b52b1856145',
  27             'thumbnail': 're:https://.*.jpg',
  28             'uploader': 'APPle5auc31995',
  29             'uploader_url': 'https://www.vidlii.com/user/APPle5auc31995',
  30             'upload_date': '20171107',
  31             'duration': 212,
  32             'view_count': int,
  33             'comment_count': int,
  34             'average_rating': float,
  35             'categories': ['News & Politics'],
  36             'tags': ['Vidlii', 'Jan', 'Videogames'],
  37         }
  38     }, {
  39         'url': 'https://www.vidlii.com/watch?v=zTAtaAgOLKt',
  40         'md5': '5778f7366aa4c569b77002f8bf6b614f',
  41         'info_dict': {
  42             'id': 'zTAtaAgOLKt',
  43             'ext': 'mp4',
  44             'title': 'FULPTUBE SUCKS.',
  45             'description': 'md5:087b2ca355d4c8f8f77e97c43e72d711',
  46             'thumbnail': 'https://www.vidlii.com/usfi/thmp/zTAtaAgOLKt.jpg',
  47             'uploader': 'Homicide',
  48             'uploader_url': 'https://www.vidlii.com/user/Homicide',
  49             'upload_date': '20210612',
  50             'duration': 89,
  51             'view_count': int,
  52             'comment_count': int,
  53             'average_rating': float,
  54             'categories': ['News & Politics'],
  55             'tags': ['fulp', 'tube', 'sucks', 'bad', 'fulptube'],
  56         },
  57     }, {
  58         'url': 'https://www.vidlii.com/embed?v=tJluaH4BJ3v&a=0',
  59         'only_matching': True,
  60     }]
  61
  62     def _real_extract(self, url):
  63         video_id = self._match_id(url)
  64
  65         webpage = self._download_webpage(
  66             'https://www.vidlii.com/watch?v=%s' % video_id, video_id)
  67         formats = []
  68
  69         sources = [source[1] for source in re.findall(
  70             r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1',
  71             webpage) or []]
  72         for source in sources:
  73             source = urljoin(url, source)
  74             height = int(self._search_regex(r'(\d+).mp4', source, 'height', default=360))
  75             if self._request_webpage(HEADRequest(source), video_id, f'Checking {height}p url', errnote=False):
  76                 formats.append({
  77                     'url': source,
  78                     'format_id': f'{height}p',
  79                     'height': height,
  80                 })
  81
  82         title = self._search_regex(
  83             (r'<h1>([^<]+)</h1>', r'<title>([^<]+) - VidLii<'), webpage,
  84             'title')
  85
  86         description = self._html_search_meta(
  87             ('description', 'twitter:description'), webpage,
  88             default=None) or strip_or_none(
  89             get_element_by_id('des_text', webpage))
  90
  91         thumbnail = self._html_search_meta(
  92             'twitter:image', webpage, default=None)
  93         if not thumbnail:
  94             thumbnail_path = self._search_regex(
  95                 r'img\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
  96                 'thumbnail', fatal=False, group='url')
  97             if thumbnail_path:
  98                 thumbnail = urljoin(url, thumbnail_path)
  99
 100         uploader = self._search_regex(
 101             r'<div[^>]+class=["\']wt_person[^>]+>\s*<a[^>]+\bhref=["\']/user/[^>]+>([^<]+)',
 102             webpage, 'uploader', fatal=False)
 103         uploader_url = format_field(uploader, None, 'https://www.vidlii.com/user/%s')
 104
 105         upload_date = unified_strdate(self._html_search_meta(
 106             'datePublished', webpage, default=None) or self._search_regex(
 107             r'<date>([^<]+)', webpage, 'upload date', fatal=False))
 108
 109         duration = int_or_none(self._html_search_meta(
 110             'video:duration', webpage, 'duration',
 111             default=None) or self._search_regex(
 112             r'duration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
 113
 114         view_count = str_to_int(self._search_regex(
 115             (r'<strong>([,0-9]+)</strong> views',
 116              r'Views\s*:\s*<strong>([,0-9]+)</strong>'),
 117             webpage, 'view count', fatal=False))
 118
 119         comment_count = int_or_none(self._search_regex(
 120             (r'<span[^>]+id=["\']cmt_num[^>]+>(\d+)',
 121              r'Comments\s*:\s*<strong>(\d+)'),
 122             webpage, 'comment count', fatal=False))
 123
 124         average_rating = float_or_none(self._search_regex(
 125             r'rating\s*:\s*([\d.]+)', webpage, 'average rating', fatal=False))
 126
 127         category = self._html_search_regex(
 128             r'<div>Category\s*:\s*</div>\s*<div>\s*<a[^>]+>([^<]+)', webpage,
 129             'category', fatal=False)
 130         categories = [category] if category else None
 131
 132         tags = [
 133             strip_or_none(tag)
 134             for tag in re.findall(
 135                 r'<a[^>]+\bhref=["\']/results\?.*?q=[^>]*>([^<]+)',
 136                 webpage) if strip_or_none(tag)
 137         ] or None
 138
 139         return {
 140             'id': video_id,
 141             'title': title,
 142             'description': description,
 143             'thumbnail': thumbnail,
 144             'uploader': uploader,
 145             'formats': formats,
 146             'uploader_url': uploader_url,
 147             'upload_date': upload_date,
 148             'duration': duration,
 149             'view_count': view_count,
 150             'comment_count': comment_count,
 151             'average_rating': average_rating,
 152             'categories': categories,
 153             'tags': tags,
 154         }