1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-14 13:25:38 +00:00
youtube-dl/youtube_dl/extractor/tvn24.py

80 lines
2.9 KiB
Python
Raw Normal View History

2017-01-11 17:49:40 +00:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
unescapeHTML,
)
2017-01-11 17:49:40 +00:00
class TVN24IE(InfoExtractor):
2017-10-03 16:28:13 +00:00
_VALID_URL = r'https?://(?:(?:[^/]+)\.)?tvn24(?:bis)?\.pl/(?:[^/]+/)*(?P<id>[^/]+)'
_TESTS = [{
2017-01-11 17:49:40 +00:00
'url': 'http://www.tvn24.pl/wiadomosci-z-kraju,3/oredzie-artura-andrusa,702428.html',
'md5': 'fbdec753d7bc29d96036808275f2130c',
'info_dict': {
'id': '1584444',
'ext': 'mp4',
'title': '"Święta mają być wesołe, dlatego, ludziska, wszyscy pod jemiołę"',
'description': 'Wyjątkowe orędzie Artura Andrusa, jednego z gości "Szkła kontaktowego".',
2017-10-03 16:28:13 +00:00
'thumbnail': 're:https?://.*[.]jpeg',
2017-01-11 17:49:40 +00:00
}
}, {
'url': 'http://fakty.tvn24.pl/ogladaj-online,60/53-konferencja-bezpieczenstwa-w-monachium,716431.html',
'only_matching': True,
}, {
'url': 'http://sport.tvn24.pl/pilka-nozna,105/ligue-1-kamil-glik-rozcial-glowe-monaco-tylko-remisuje-z-bastia,716522.html',
'only_matching': True,
}, {
'url': 'http://tvn24bis.pl/poranek,146,m/gen-koziej-w-tvn24-bis-wracamy-do-czasow-zimnej-wojny,715660.html',
'only_matching': True,
2017-10-03 16:28:13 +00:00
}, {
'url': 'https://www.tvn24.pl/magazyn-tvn24/angie-w-jednej-czwartej-polka-od-szarej-myszki-do-cesarzowej-europy,119,2158',
'only_matching': True,
}]
2017-01-11 17:49:40 +00:00
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
2017-01-11 17:49:40 +00:00
title = self._og_search_title(webpage)
def extract_json(attr, name, fatal=True):
return self._parse_json(
self._search_regex(
r'\b%s=(["\'])(?P<json>(?!\1).+?)\1' % attr, webpage,
name, group='json', fatal=fatal) or '{}',
video_id, transform_source=unescapeHTML, fatal=fatal)
quality_data = extract_json('data-quality', 'formats')
2017-01-11 17:49:40 +00:00
formats = []
for format_id, url in quality_data.items():
formats.append({
'url': url,
'format_id': format_id,
'height': int_or_none(format_id.rstrip('p')),
2017-01-11 17:49:40 +00:00
})
self._sort_formats(formats)
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(
webpage, default=None) or self._html_search_regex(
r'\bdata-poster=(["\'])(?P<url>(?!\1).+?)\1', webpage,
'thumbnail', group='url')
share_params = extract_json(
'data-share-params', 'share params', fatal=False)
if isinstance(share_params, dict):
video_id = share_params.get('id') or video_id
2017-01-11 17:49:40 +00:00
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'formats': formats,
}