[pladform] Respect platform id and extract HLS formats (closes #15468)

This commit is contained in:
Sergey M․ 2018-02-02 03:07:30 +07:00
parent 64a12edb48
commit 3c3bceb41d
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D

View File

@ -4,7 +4,9 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import ( from ..utils import (
determine_ext,
ExtractorError, ExtractorError,
int_or_none, int_or_none,
xpath_text, xpath_text,
@ -26,17 +28,15 @@ class PladformIE(InfoExtractor):
(?P<id>\d+) (?P<id>\d+)
''' '''
_TESTS = [{ _TESTS = [{
# http://muz-tv.ru/kinozal/view/7400/ 'url': 'https://out.pladform.ru/player?pl=64471&videoid=3777899&vk_puid15=0&vk_puid34=0',
'url': 'http://out.pladform.ru/player?pl=24822&videoid=100183293', 'md5': '53362fac3a27352da20fa2803cc5cd6f',
'md5': '61f37b575dd27f1bb2e1854777fe31f4',
'info_dict': { 'info_dict': {
'id': '100183293', 'id': '3777899',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Тайны перевала Дятлова • 1 серия 2 часть', 'title': 'СТУДИЯ СОЮЗ • Шоу Студия Союз, 24 выпуск (01.02.2018) Нурлан Сабуров и Слава Комиссаренко',
'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века', 'description': 'md5:05140e8bf1b7e2d46e7ba140be57fd95',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'duration': 694, 'duration': 3190,
'age_limit': 0,
}, },
}, { }, {
'url': 'http://static.pladform.ru/player.swf?pl=21469&videoid=100183293&vkcid=0', 'url': 'http://static.pladform.ru/player.swf?pl=21469&videoid=100183293&vkcid=0',
@ -56,22 +56,48 @@ class PladformIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
pl = qs.get('pl', ['1'])[0]
video = self._download_xml( video = self._download_xml(
'http://out.pladform.ru/getVideo?pl=1&videoid=%s' % video_id, 'http://out.pladform.ru/getVideo', video_id, query={
video_id) 'pl': pl,
'videoid': video_id,
})
def fail(text):
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, text),
expected=True)
if video.tag == 'error': if video.tag == 'error':
raise ExtractorError( fail(video.text)
'%s returned error: %s' % (self.IE_NAME, video.text),
expected=True)
quality = qualities(('ld', 'sd', 'hd')) quality = qualities(('ld', 'sd', 'hd'))
formats = [{ formats = []
for src in video.findall('./src'):
if src is None:
continue
format_url = src.text
if not format_url:
continue
if src.get('type') == 'hls' or determine_ext(format_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
else:
formats.append({
'url': src.text, 'url': src.text,
'format_id': src.get('quality'), 'format_id': src.get('quality'),
'quality': quality(src.get('quality')), 'quality': quality(src.get('quality')),
} for src in video.findall('./src')] })
if not formats:
error = xpath_text(video, './cap', 'error', default=None)
if error:
fail(error)
self._sort_formats(formats) self._sort_formats(formats)
webpage = self._download_webpage( webpage = self._download_webpage(