[sportbox:embed] Fix extraction

This commit is contained in:
Sergey M․ 2017-07-22 21:35:14 +07:00
parent 359aa2fdd1
commit 327c8364f1
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D

View file

@ -4,7 +4,11 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import js_to_json from ..utils import (
determine_ext,
int_or_none,
js_to_json,
)
class SportBoxEmbedIE(InfoExtractor): class SportBoxEmbedIE(InfoExtractor):
@ -14,8 +18,10 @@ class SportBoxEmbedIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '211355', 'id': '211355',
'ext': 'mp4', 'ext': 'mp4',
'title': 'В Новороссийске прошел детский турнир «Поле славы боевой»', 'title': '211355',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'duration': 292,
'view_count': int,
}, },
'params': { 'params': {
# m3u8 download # m3u8 download
@ -24,6 +30,9 @@ class SportBoxEmbedIE(InfoExtractor):
}, { }, {
'url': 'http://news.sportbox.ru/vdl/player?nid=370908&only_player=1&autostart=false&playeri=2&height=340&width=580', 'url': 'http://news.sportbox.ru/vdl/player?nid=370908&only_player=1&autostart=false&playeri=2&height=340&width=580',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://news.sportbox.ru/vdl/player/media/193095',
'only_matching': True,
}] }]
@staticmethod @staticmethod
@ -37,36 +46,34 @@ class SportBoxEmbedIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
wjplayer_data = self._parse_json(
self._search_regex(
r'(?s)wjplayer\(({.+?})\);', webpage, 'wjplayer settings'),
video_id, transform_source=js_to_json)
formats = [] formats = []
for source in wjplayer_data['sources']:
def cleanup_js(code): src = source.get('src')
# desktop_advert_config contains complex Javascripts and we don't need it if not src:
return js_to_json(re.sub(r'desktop_advert_config.*', '', code)) continue
if determine_ext(src) == 'm3u8':
jwplayer_data = self._parse_json(self._search_regex(
r'(?s)player\.setup\(({.+?})\);', webpage, 'jwplayer settings'), video_id,
transform_source=cleanup_js)
hls_url = jwplayer_data.get('hls_url')
if hls_url:
formats.extend(self._extract_m3u8_formats( formats.extend(self._extract_m3u8_formats(
hls_url, video_id, ext='mp4', m3u8_id='hls')) src, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
rtsp_url = jwplayer_data.get('rtsp_url') else:
if rtsp_url:
formats.append({ formats.append({
'url': rtsp_url, 'url': src,
'format_id': 'rtsp',
}) })
self._sort_formats(formats) self._sort_formats(formats)
title = jwplayer_data['node_title'] view_count = int_or_none(self._search_regex(
thumbnail = jwplayer_data.get('image_url') r'Просмотров\s*:\s*(\d+)', webpage, 'view count', default=None))
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': video_id,
'thumbnail': thumbnail, 'thumbnail': wjplayer_data.get('poster'),
'duration': int_or_none(wjplayer_data.get('duration')),
'view_count': view_count,
'formats': formats, 'formats': formats,
} }