yt_dlp/extractor/vidlii.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     HEADRequest,
   9     float_or_none,
  10     get_element_by_id,
  11     int_or_none,
  12     str_to_int,
  13     strip_or_none,
  14     unified_strdate,
  15     urljoin,
  16 )
  17
  18
  19 class VidLiiIE(InfoExtractor):
  20     _VALID_URL = r'https?://(?:www\.)?vidlii\.com/(?:watch|embed)\?.*?\bv=(?P<id>[0-9A-Za-z_-]{11})'
  21     _TESTS = [{
  22         'url': 'https://www.vidlii.com/watch?v=tJluaH4BJ3v',
  23         'md5': '9bf7d1e005dfa909b6efb0a1ff5175e2',
  24         'info_dict': {
  25             'id': 'tJluaH4BJ3v',
  26             'ext': 'mp4',
  27             'title': 'Vidlii is against me',
  28             'description': 'md5:fa3f119287a2bfb922623b52b1856145',
  29             'thumbnail': 're:https://.*.jpg',
  30             'uploader': 'APPle5auc31995',
  31             'uploader_url': 'https://www.vidlii.com/user/APPle5auc31995',
  32             'upload_date': '20171107',
  33             'duration': 212,
  34             'view_count': int,
  35             'comment_count': int,
  36             'average_rating': float,
  37             'categories': ['News & Politics'],
  38             'tags': ['Vidlii', 'Jan', 'Videogames'],
  39         }
  40     }, {
  41         'url': 'https://www.vidlii.com/watch?v=zTAtaAgOLKt',
  42         'md5': '5778f7366aa4c569b77002f8bf6b614f',
  43         'info_dict': {
  44             'id': 'zTAtaAgOLKt',
  45             'ext': 'mp4',
  46             'title': 'FULPTUBE SUCKS.',
  47             'description': 'md5:087b2ca355d4c8f8f77e97c43e72d711',
  48             'thumbnail': 'https://www.vidlii.com/usfi/thmp/zTAtaAgOLKt.jpg',
  49             'uploader': 'Homicide',
  50             'uploader_url': 'https://www.vidlii.com/user/Homicide',
  51             'upload_date': '20210612',
  52             'duration': 89,
  53             'view_count': int,
  54             'comment_count': int,
  55             'average_rating': float,
  56             'categories': ['News & Politics'],
  57             'tags': ['fulp', 'tube', 'sucks', 'bad', 'fulptube'],
  58         },
  59     }, {
  60         'url': 'https://www.vidlii.com/embed?v=tJluaH4BJ3v&a=0',
  61         'only_matching': True,
  62     }]
  63
  64     def _real_extract(self, url):
  65         video_id = self._match_id(url)
  66
  67         webpage = self._download_webpage(
  68             'https://www.vidlii.com/watch?v=%s' % video_id, video_id)
  69         formats = []
  70
  71         sources = [source[1] for source in re.findall(
  72             r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1',
  73             webpage) or []]
  74         for source in sources:
  75             height = int(self._search_regex(r'(\d+).mp4', source, 'height', default=360))
  76             if self._request_webpage(HEADRequest(source), video_id, f'Checking {height}p url', errnote=False):
  77                 formats.append({
  78                     'url': source,
  79                     'format_id': f'{height}p',
  80                     'height': height,
  81                 })
  82         self._sort_formats(formats)
  83
  84         title = self._search_regex(
  85             (r'<h1>([^<]+)</h1>', r'<title>([^<]+) - VidLii<'), webpage,
  86             'title')
  87
  88         description = self._html_search_meta(
  89             ('description', 'twitter:description'), webpage,
  90             default=None) or strip_or_none(
  91             get_element_by_id('des_text', webpage))
  92
  93         thumbnail = self._html_search_meta(
  94             'twitter:image', webpage, default=None)
  95         if not thumbnail:
  96             thumbnail_path = self._search_regex(
  97                 r'img\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
  98                 'thumbnail', fatal=False, group='url')
  99             if thumbnail_path:
 100                 thumbnail = urljoin(url, thumbnail_path)
 101
 102         uploader = self._search_regex(
 103             r'<div[^>]+class=["\']wt_person[^>]+>\s*<a[^>]+\bhref=["\']/user/[^>]+>([^<]+)',
 104             webpage, 'uploader', fatal=False)
 105         uploader_url = 'https://www.vidlii.com/user/%s' % uploader if uploader else None
 106
 107         upload_date = unified_strdate(self._html_search_meta(
 108             'datePublished', webpage, default=None) or self._search_regex(
 109             r'<date>([^<]+)', webpage, 'upload date', fatal=False))
 110
 111         duration = int_or_none(self._html_search_meta(
 112             'video:duration', webpage, 'duration',
 113             default=None) or self._search_regex(
 114             r'duration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
 115
 116         view_count = str_to_int(self._search_regex(
 117             (r'<strong>([,0-9]+)</strong> views',
 118              r'Views\s*:\s*<strong>([,0-9]+)</strong>'),
 119             webpage, 'view count', fatal=False))
 120
 121         comment_count = int_or_none(self._search_regex(
 122             (r'<span[^>]+id=["\']cmt_num[^>]+>(\d+)',
 123              r'Comments\s*:\s*<strong>(\d+)'),
 124             webpage, 'comment count', fatal=False))
 125
 126         average_rating = float_or_none(self._search_regex(
 127             r'rating\s*:\s*([\d.]+)', webpage, 'average rating', fatal=False))
 128
 129         category = self._html_search_regex(
 130             r'<div>Category\s*:\s*</div>\s*<div>\s*<a[^>]+>([^<]+)', webpage,
 131             'category', fatal=False)
 132         categories = [category] if category else None
 133
 134         tags = [
 135             strip_or_none(tag)
 136             for tag in re.findall(
 137                 r'<a[^>]+\bhref=["\']/results\?.*?q=[^>]*>([^<]+)',
 138                 webpage) if strip_or_none(tag)
 139         ] or None
 140
 141         return {
 142             'id': video_id,
 143             'title': title,
 144             'description': description,
 145             'thumbnail': thumbnail,
 146             'uploader': uploader,
 147             'formats': formats,
 148             'uploader_url': uploader_url,
 149             'upload_date': upload_date,
 150             'duration': duration,
 151             'view_count': view_count,
 152             'comment_count': comment_count,
 153             'average_rating': average_rating,
 154             'categories': categories,
 155             'tags': tags,
 156         }