yt_dlp/extractor/nzonscreen.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     float_or_none,
   4     int_or_none,
   5     remove_end,
   6     strip_or_none,
   7     traverse_obj,
   8     url_or_none,
   9 )
  10
  11
  12 class NZOnScreenIE(InfoExtractor):
  13     _VALID_URL = r'https?://www\.nzonscreen\.com/title/(?P<id>[^/?#]+)'
  14     _TESTS = [{
  15         'url': 'https://www.nzonscreen.com/title/shoop-shoop-diddy-wop-cumma-cumma-wang-dang-1982',
  16         'info_dict': {
  17             'id': '726ed6585c6bfb30',
  18             'ext': 'mp4',
  19             'format_id': 'hi',
  20             'display_id': 'shoop-shoop-diddy-wop-cumma-cumma-wang-dang-1982',
  21             'title': 'Monte Video - "Shoop Shoop, Diddy Wop"',
  22             'description': 'Monte Video - "Shoop Shoop, Diddy Wop"',
  23             'alt_title': 'Shoop Shoop Diddy Wop Cumma Cumma Wang Dang | Music Video',
  24             'thumbnail': r're:https://www\.nzonscreen\.com/content/images/.+\.jpg',
  25             'duration': 158,
  26         },
  27         'params': {'skip_download': 'm3u8'},
  28     }, {
  29         'url': 'https://www.nzonscreen.com/title/shes-a-mod-1964?collection=best-of-the-60s',
  30         'info_dict': {
  31             'id': '3dbe709ff03c36f1',
  32             'ext': 'mp4',
  33             'format_id': 'hi',
  34             'display_id': 'shes-a-mod-1964',
  35             'title': 'Ray Columbus - \'She\'s A Mod\'',
  36             'description': 'Ray Columbus - \'She\'s A Mod\'',
  37             'alt_title': 'She\'s a Mod | Music Video',
  38             'thumbnail': r're:https://www\.nzonscreen\.com/content/images/.+\.jpg',
  39             'duration': 130,
  40         },
  41         'params': {'skip_download': 'm3u8'},
  42     }, {
  43         'url': 'https://www.nzonscreen.com/title/puha-and-pakeha-1968/overview',
  44         'info_dict': {
  45             'id': 'f86342544385ad8a',
  46             'ext': 'mp4',
  47             'format_id': 'hi',
  48             'display_id': 'puha-and-pakeha-1968',
  49             'title': 'Looking At New Zealand - Puha and Pakeha',
  50             'alt_title': 'Looking at New Zealand - \'Pūhā and Pākehā\' | Television',
  51             'description': 'An excerpt from this television programme.',
  52             'duration': 212,
  53             'thumbnail': r're:https://www\.nzonscreen\.com/content/images/.+\.jpg',
  54         },
  55         'params': {'skip_download': 'm3u8'},
  56     }]
  57
  58     def _extract_formats(self, playlist):
  59         for quality, (id_, url) in enumerate(traverse_obj(
  60                 playlist, ('h264', {'lo': 'lo_res', 'hi': 'hi_res'}), expected_type=url_or_none).items()):
  61             yield {
  62                 'url': url,
  63                 'format_id': id_,
  64                 'ext': 'mp4',
  65                 'quality': quality,
  66                 'height': int_or_none(playlist.get('height')) if id_ == 'hi' else None,
  67                 'width': int_or_none(playlist.get('width')) if id_ == 'hi' else None,
  68                 'filesize_approx': float_or_none(traverse_obj(playlist, ('h264', f'{id_}_res_mb')), invscale=1024**2),
  69             }
  70
  71     def _real_extract(self, url):
  72         video_id = self._match_id(url)
  73         webpage = self._download_webpage(url, video_id)
  74
  75         playlist = self._parse_json(self._html_search_regex(
  76             r'data-video-config=\'([^\']+)\'', webpage, 'media data'), video_id)
  77
  78         return {
  79             'id': playlist['uuid'],
  80             'display_id': video_id,
  81             'title': strip_or_none(playlist.get('label')),
  82             'description': strip_or_none(playlist.get('description')),
  83             'alt_title': strip_or_none(remove_end(
  84                 self._html_extract_title(webpage, default=None) or self._og_search_title(webpage),
  85                 ' | NZ On Screen')),
  86             'thumbnail': traverse_obj(playlist, ('thumbnail', 'path')),
  87             'duration': float_or_none(playlist.get('duration')),
  88             'formats': list(self._extract_formats(playlist)),
  89             'http_headers': {
  90                 'Referer': 'https://www.nzonscreen.com/',
  91                 'Origin': 'https://www.nzonscreen.com/',
  92             },
  93         }