1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
youtube-dl/youtube_dl/extractor/sportbox.py

100 lines
3.3 KiB
Python
Raw Permalink Normal View History

# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2017-07-22 14:35:14 +00:00
from ..utils import (
determine_ext,
int_or_none,
js_to_json,
merge_dicts,
2017-07-22 14:35:14 +00:00
)
class SportBoxIE(InfoExtractor):
_VALID_URL = r'https?://(?:news\.sportbox|matchtv)\.ru/vdl/player(?:/[^/]+/|\?.*?\bn?id=)(?P<id>\d+)'
2015-05-15 16:50:44 +00:00
_TESTS = [{
'url': 'http://news.sportbox.ru/vdl/player/ci/211355',
'info_dict': {
'id': '109158',
2015-05-15 16:50:44 +00:00
'ext': 'mp4',
2018-10-26 08:00:55 +00:00
'title': 'В Новороссийске прошел детский турнир «Поле славы боевой»',
'description': 'В Новороссийске прошел детский турнир «Поле славы боевой»',
'thumbnail': r're:^https?://.*\.jpg$',
2017-07-22 14:35:14 +00:00
'duration': 292,
'view_count': int,
'timestamp': 1426237001,
'upload_date': '20150313',
2015-05-15 16:50:44 +00:00
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://news.sportbox.ru/vdl/player?nid=370908&only_player=1&autostart=false&playeri=2&height=340&width=580',
'only_matching': True,
2017-07-22 14:35:14 +00:00
}, {
'url': 'https://news.sportbox.ru/vdl/player/media/193095',
'only_matching': True,
}, {
'url': 'https://news.sportbox.ru/vdl/player/media/109158',
'only_matching': True,
}, {
'url': 'https://matchtv.ru/vdl/player/media/109158',
'only_matching': True,
2015-05-15 16:50:44 +00:00
}]
2015-05-15 17:08:44 +00:00
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe[^>]+src="(https?://(?:news\.sportbox|matchtv)\.ru/vdl/player[^"]+)"',
2015-05-15 17:08:44 +00:00
webpage)
2015-05-15 16:50:44 +00:00
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
sources = self._parse_json(
2018-10-26 08:00:55 +00:00
self._search_regex(
r'(?s)playerOptions\.sources(?:WithRes)?\s*=\s*(\[.+?\])\s*;\s*\n',
webpage, 'sources'),
2018-10-26 08:00:55 +00:00
video_id, transform_source=js_to_json)
2017-07-22 14:35:14 +00:00
formats = []
for source in sources:
2017-07-22 14:35:14 +00:00
src = source.get('src')
if not src:
continue
if determine_ext(src) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
src, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
else:
formats.append({
'url': src,
})
self._sort_formats(formats)
2015-05-15 16:50:44 +00:00
player = self._parse_json(
self._search_regex(
r'(?s)playerOptions\s*=\s*({.+?})\s*;\s*\n', webpage,
'player options', default='{}'),
video_id, transform_source=js_to_json)
media_id = player['mediaId']
info = self._search_json_ld(webpage, media_id, default={})
2017-07-22 14:35:14 +00:00
view_count = int_or_none(self._search_regex(
r'Просмотров\s*:\s*(\d+)', webpage, 'view count', default=None))
2015-05-15 16:50:44 +00:00
return merge_dicts(info, {
'id': media_id,
'title': self._og_search_title(webpage, default=None) or media_id,
'thumbnail': player.get('poster'),
'duration': int_or_none(player.get('duration')),
2017-07-22 14:35:14 +00:00
'view_count': view_count,
'formats': formats,
})