1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-02 09:12:40 +01:00
yt-dlp/youtube_dl/extractor/sportbox.py
Vitaliy Syrchikov e9ca615a98 New test
2015-05-15 19:57:54 +04:00

100 lines
4.0 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
parse_duration,
parse_iso8601,
)
class SportBoxIE(InfoExtractor):
_VALID_URL = r'https?://news\.sportbox\.ru/(?:[^/]+/)+spbvideo_NI\d+_(?P<display_id>.+)'
_TESTS = [
{
'url': 'http://news.sportbox.ru/Vidy_sporta/Avtosport/Rossijskij/spbvideo_NI483529_Gonka-2-zaezd-Obyedinenniy-2000-klassi-Turing-i-S',
'md5': 'ff56a598c2cf411a9a38a69709e97079',
'info_dict': {
'id': '80822',
'ext': 'mp4',
'title': 'Гонка 2 заезд ««Объединенный 2000»: классы Туринг и Супер-продакшн',
'description': 'md5:81715fa9c4ea3d9e7915dc8180c778ed',
'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': 1411896237,
'upload_date': '20140928',
'duration': 4846,
},
'params': {
# m3u8 download
'skip_download': True,
},
},
{
'url': 'http://news.sportbox.ru/video/no_ads/spbvideo_NI536574_V_Novorossijske_proshel_detskij_turnir_Pole_slavy_bojevoj?ci=211355',
'md5': 'ff56a598c2cf411a9a38a69709e97079',
'info_dict': {
'id': '211355',
'ext': 'mp4',
'title': 'В Новороссийске прошел детский турнир «Поле славы боевой»',
'description': '16 детских коллективов приняли участие в суперфинале турнира «Поле славы боевой».',
'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': 1426237001,
'upload_date': '20150313',
'duration': 292,
},
'params': {
# m3u8 download
'skip_download': True,
},
},
{
'url': 'http://news.sportbox.ru/Vidy_sporta/billiard/spbvideo_NI486287_CHempionat-mira-po-dinamichnoy-piramide-4',
'only_matching': True,
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
sobj = re.search(r'src="/vdl/player/(?P<media_type>\w+)/(?P<video_id>\d+)"', webpage)
if (sobj):
video_id = sobj.group('video_id')
media_type = sobj.group('media_type')
else:
raise RegexNotFoundError('Unable to extract video_id')
player = self._download_webpage(
'http://news.sportbox.ru/vdl/player/%s/%s' % (media_type, video_id),
display_id, 'Downloading player webpage')
hls = self._search_regex(
r"sportboxPlayer\.jwplayer_common_params\.file\s*=\s*['\"]+([^\"]+)['\"]+", player, 'hls file')
formats = self._extract_m3u8_formats(hls, display_id, 'mp4')
title = self._html_search_regex(
r'<h1 itemprop="name">([^<]+)</h1>', webpage, 'title')
description = self._html_search_regex(
r'(?s)<div itemprop="description">(.+?)</div>', webpage, 'description', fatal=False)
thumbnail = self._og_search_thumbnail(webpage)
timestamp = parse_iso8601(self._search_regex(
r'<span itemprop="uploadDate">([^<]+)</span>', webpage, 'timestamp', fatal=False))
duration = parse_duration(self._html_search_regex(
r'<meta itemprop="duration" content="PT([^"]+)">', webpage, 'duration', fatal=False))
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
'duration': duration,
'formats': formats,
}