yt_dlp/extractor/euscreen.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6 from ..utils import (
   7     parse_duration,
   8     js_to_json,
   9 )
  10
  11
  12 class EUScreenIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?euscreen\.eu/item.html\?id=(?P<id>[^&?$/]+)'
  14
  15     _TESTS = [{
  16         'url': 'https://euscreen.eu/item.html?id=EUS_0EBCBF356BFC4E12A014023BA41BD98C',
  17         'info_dict': {
  18             'id': 'EUS_0EBCBF356BFC4E12A014023BA41BD98C',
  19             'ext': 'mp4',
  20             'title': "L'effondrement du stade du Heysel",
  21             'alt_title': 'Collapse of the Heysel Stadium',
  22             'duration': 318.0,
  23             'description': 'md5:f0ffffdfce6821139357a1b8359d6152',
  24             'series': 'JA2 DERNIERE',
  25             'episode': '-',
  26             'uploader': 'INA /  France',
  27             'thumbnail': 'http://images3.noterik.com/domain/euscreenxl/user/eu_ina/video/EUS_0EBCBF356BFC4E12A014023BA41BD98C/image.jpg'
  28         },
  29         'params': {'skip_download': True}
  30     }]
  31
  32     _payload = b'<fsxml><screen><properties><screenId>-1</screenId></properties><capabilities id="1"><properties><platform>Win32</platform><appcodename>Mozilla</appcodename><appname>Netscape</appname><appversion>5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36</appversion><useragent>Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36</useragent><cookiesenabled>true</cookiesenabled><screenwidth>784</screenwidth><screenheight>758</screenheight><orientation>undefined</orientation><smt_browserid>Sat, 07 Oct 2021 08:56:50 GMT</smt_browserid><smt_sessionid>1633769810758</smt_sessionid></properties></capabilities></screen></fsxml>'
  33
  34     def _real_extract(self, url):
  35         id = self._match_id(url)
  36         args_for_js_request = self._download_webpage(
  37             'https://euscreen.eu/lou/LouServlet/domain/euscreenxl/html5application/euscreenxlitem',
  38             id, data=self._payload, query={'actionlist': 'itempage', 'id': id})
  39         info_js = self._download_webpage(
  40             'https://euscreen.eu/lou/LouServlet/domain/euscreenxl/html5application/euscreenxlitem',
  41             id, data=args_for_js_request.replace('screenid', 'screenId').encode())
  42         video_json = self._parse_json(
  43             self._search_regex(r'setVideo\(({.+})\)\(\$end\$\)put', info_js, 'Video JSON'),
  44             id, transform_source=js_to_json)
  45         meta_json = self._parse_json(
  46             self._search_regex(r'setData\(({.+})\)\(\$end\$\)', info_js, 'Metadata JSON'),
  47             id, transform_source=js_to_json)
  48         formats = [{
  49             'url': source['src'],
  50         } for source in video_json.get('sources', [])]
  51         self._sort_formats(formats)
  52
  53         return {
  54             'id': id,
  55             'title': meta_json.get('originalTitle'),
  56             'alt_title': meta_json.get('title'),
  57             'duration': parse_duration(meta_json.get('duration')),
  58             'description': '%s\n%s' % (meta_json.get('summaryOriginal', ''), meta_json.get('summaryEnglish', '')),
  59             'series': meta_json.get('series') or meta_json.get('seriesEnglish'),
  60             'episode': meta_json.get('episodeNumber'),
  61             'uploader': meta_json.get('provider'),
  62             'thumbnail': meta_json.get('screenshot') or video_json.get('screenshot'),
  63             'formats': formats,
  64         }