yt_dlp/extractor/biqle.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from .vk import VKIE
   6 from ..compat import compat_b64decode
   7 from ..utils import (
   8     int_or_none,
   9     js_to_json,
  10     traverse_obj,
  11     unified_timestamp,
  12 )
  13
  14
  15 class BIQLEIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?biqle\.(?:com|org|ru)/watch/(?P<id>-?\d+_\d+)'
  17     _TESTS = [{
  18         'url': 'https://biqle.ru/watch/-2000421746_85421746',
  19         'md5': 'ae6ef4f04d19ac84e4658046d02c151c',
  20         'info_dict': {
  21             'id': '-2000421746_85421746',
  22             'ext': 'mp4',
  23             'title': 'Forsaken By Hope Studio Clip',
  24             'description': 'Forsaken By Hope Studio Clip — Смотреть онлайн',
  25             'upload_date': '19700101',
  26             'thumbnail': r're:https://[^/]+/impf/7vN3ACwSTgChP96OdOfzFjUCzFR6ZglDQgWsIw/KPaACiVJJxM\.jpg\?size=800x450&quality=96&keep_aspect_ratio=1&background=000000&sign=b48ea459c4d33dbcba5e26d63574b1cb&type=video_thumb',
  27             'timestamp': 0,
  28         },
  29     }, {
  30         'url': 'http://biqle.org/watch/-44781847_168547604',
  31         'md5': '7f24e72af1db0edf7c1aaba513174f97',
  32         'info_dict': {
  33             'id': '-44781847_168547604',
  34             'ext': 'mp4',
  35             'title': 'Ребенок в шоке от автоматической мойки',
  36             'description': 'Ребенок в шоке от автоматической мойки — Смотреть онлайн',
  37             'timestamp': 1396633454,
  38             'upload_date': '20140404',
  39             'thumbnail': r're:https://[^/]+/c535507/u190034692/video/l_b84df002\.jpg',
  40         },
  41     }]
  42
  43     def _real_extract(self, url):
  44         video_id = self._match_id(url)
  45         webpage = self._download_webpage(url, video_id)
  46
  47         title = self._html_search_meta('name', webpage, 'Title', fatal=False)
  48         timestamp = unified_timestamp(self._html_search_meta('uploadDate', webpage, 'Upload Date', default=None))
  49         description = self._html_search_meta('description', webpage, 'Description', default=None)
  50
  51         global_embed_url = self._search_regex(
  52             r'<script[^<]+?window.globEmbedUrl\s*=\s*\'((?:https?:)?//(?:daxab\.com|dxb\.to|[^/]+/player)/[^\']+)\'',
  53             webpage, 'global Embed url')
  54         hash = self._search_regex(
  55             r'<script id="data-embed-video[^<]+?hash: "([^"]+)"[^<]*</script>', webpage, 'Hash')
  56
  57         embed_url = global_embed_url + hash
  58
  59         if VKIE.suitable(embed_url):
  60             return self.url_result(embed_url, VKIE.ie_key(), video_id)
  61
  62         embed_page = self._download_webpage(
  63             embed_url, video_id, 'Downloading embed webpage', headers={'Referer': url})
  64
  65         glob_params = self._parse_json(self._search_regex(
  66             r'<script id="globParams">[^<]*window.globParams = ([^;]+);[^<]+</script>',
  67             embed_page, 'Global Parameters'), video_id, transform_source=js_to_json)
  68         host_name = compat_b64decode(glob_params['server'][::-1]).decode()
  69
  70         item = self._download_json(
  71             f'https://{host_name}/method/video.get/{video_id}', video_id,
  72             headers={'Referer': url}, query={
  73                 'token': glob_params['video']['access_token'],
  74                 'videos': video_id,
  75                 'ckey': glob_params['c_key'],
  76                 'credentials': glob_params['video']['credentials'],
  77             })['response']['items'][0]
  78
  79         formats = []
  80         for f_id, f_url in item.get('files', {}).items():
  81             if f_id == 'external':
  82                 return self.url_result(f_url)
  83             ext, height = f_id.split('_')
  84             height_extra_key = traverse_obj(glob_params, ('video', 'partial', 'quality', height))
  85             if height_extra_key:
  86                 formats.append({
  87                     'format_id': f'{height}p',
  88                     'url': f'https://{host_name}/{f_url[8:]}&videos={video_id}&extra_key={height_extra_key}',
  89                     'height': int_or_none(height),
  90                     'ext': ext,
  91                 })
  92         self._sort_formats(formats)
  93
  94         thumbnails = []
  95         for k, v in item.items():
  96             if k.startswith('photo_') and v:
  97                 width = k.replace('photo_', '')
  98                 thumbnails.append({
  99                     'id': width,
 100                     'url': v,
 101                     'width': int_or_none(width),
 102                 })
 103
 104         return {
 105             'id': video_id,
 106             'title': title,
 107             'formats': formats,
 108             'comment_count': int_or_none(item.get('comments')),
 109             'description': description,
 110             'duration': int_or_none(item.get('duration')),
 111             'thumbnails': thumbnails,
 112             'timestamp': timestamp,
 113             'view_count': int_or_none(item.get('views')),
 114         }