[videomore] Improve extraction and fix season extractor (closes #18908)

This commit is contained in:
Sergey M․ 2019-01-22 03:03:53 +07:00
parent 07f9febc4b
commit 19d6991312
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D

View File

@ -4,8 +4,14 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
orderedSet,
parse_duration,
str_or_none,
unified_strdate,
url_or_none,
xpath_element, xpath_element,
xpath_text, xpath_text,
) )
@ -13,7 +19,19 @@ from ..utils import (
class VideomoreIE(InfoExtractor): class VideomoreIE(InfoExtractor):
IE_NAME = 'videomore' IE_NAME = 'videomore'
_VALID_URL = r'videomore:(?P<sid>\d+)$|https?://videomore\.ru/(?:(?:embed|[^/]+/[^/]+)/|[^/]+\?.*\btrack_id=)(?P<id>\d+)(?:[/?#&]|\.(?:xml|json)|$)' _VALID_URL = r'''(?x)
videomore:(?P<sid>\d+)$|
https?://(?:player\.)?videomore\.ru/
(?:
(?:
embed|
[^/]+/[^/]+
)/|
[^/]*\?.*?\btrack_id=
)
(?P<id>\d+)
(?:[/?#&]|\.(?:xml|json)|$)
'''
_TESTS = [{ _TESTS = [{
'url': 'http://videomore.ru/kino_v_detalayah/5_sezon/367617', 'url': 'http://videomore.ru/kino_v_detalayah/5_sezon/367617',
'md5': '44455a346edc0d509ac5b5a5b531dc35', 'md5': '44455a346edc0d509ac5b5a5b531dc35',
@ -79,6 +97,9 @@ class VideomoreIE(InfoExtractor):
}, { }, {
'url': 'videomore:367617', 'url': 'videomore:367617',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://player.videomore.ru/?partner_id=97&track_id=736234&autoplay=0&userToken=',
'only_matching': True,
}] }]
@staticmethod @staticmethod
@ -136,7 +157,7 @@ class VideomoreIE(InfoExtractor):
class VideomoreVideoIE(InfoExtractor): class VideomoreVideoIE(InfoExtractor):
IE_NAME = 'videomore:video' IE_NAME = 'videomore:video'
_VALID_URL = r'https?://videomore\.ru/(?:(?:[^/]+/){2})?(?P<id>[^/?#&]+)[/?#&]*$' _VALID_URL = r'https?://videomore\.ru/(?:(?:[^/]+/){2})?(?P<id>[^/?#&]+)(?:/*|[?#&].*?)$'
_TESTS = [{ _TESTS = [{
# single video with og:video:iframe # single video with og:video:iframe
'url': 'http://videomore.ru/elki_3', 'url': 'http://videomore.ru/elki_3',
@ -176,6 +197,9 @@ class VideomoreVideoIE(InfoExtractor):
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
}, {
'url': 'https://videomore.ru/molodezhka/6_sezon/29_seriya?utm_so',
'only_matching': True,
}] }]
@classmethod @classmethod
@ -196,13 +220,16 @@ class VideomoreVideoIE(InfoExtractor):
r'track-id=["\'](\d+)', r'track-id=["\'](\d+)',
r'xcnt_product_id\s*=\s*(\d+)'), webpage, 'video id') r'xcnt_product_id\s*=\s*(\d+)'), webpage, 'video id')
video_url = 'videomore:%s' % video_id video_url = 'videomore:%s' % video_id
else:
video_id = None
return self.url_result(video_url, VideomoreIE.ie_key()) return self.url_result(
video_url, ie=VideomoreIE.ie_key(), video_id=video_id)
class VideomoreSeasonIE(InfoExtractor): class VideomoreSeasonIE(InfoExtractor):
IE_NAME = 'videomore:season' IE_NAME = 'videomore:season'
_VALID_URL = r'https?://videomore\.ru/(?!embed)(?P<id>[^/]+/[^/?#&]+)[/?#&]*$' _VALID_URL = r'https?://videomore\.ru/(?!embed)(?P<id>[^/]+/[^/?#&]+)(?:/*|[?#&].*?)$'
_TESTS = [{ _TESTS = [{
'url': 'http://videomore.ru/molodezhka/sezon_promo', 'url': 'http://videomore.ru/molodezhka/sezon_promo',
'info_dict': { 'info_dict': {
@ -210,8 +237,16 @@ class VideomoreSeasonIE(InfoExtractor):
'title': 'Молодежка Промо', 'title': 'Молодежка Промо',
}, },
'playlist_mincount': 12, 'playlist_mincount': 12,
}, {
'url': 'http://videomore.ru/molodezhka/sezon_promo?utm_so',
'only_matching': True,
}] }]
@classmethod
def suitable(cls, url):
return (False if (VideomoreIE.suitable(url) or VideomoreVideoIE.suitable(url))
else super(VideomoreSeasonIE, cls).suitable(url))
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
@ -219,6 +254,51 @@ class VideomoreSeasonIE(InfoExtractor):
title = self._og_search_title(webpage) title = self._og_search_title(webpage)
data = self._parse_json(
self._html_search_regex(
r'\bclass=["\']seasons-tracks["\'][^>]+\bdata-custom-data=(["\'])(?P<value>{.+?})\1',
webpage, 'data', default='{}', group='value'),
display_id, fatal=False)
entries = []
if data:
episodes = data.get('episodes')
if isinstance(episodes, list):
for ep in episodes:
if not isinstance(ep, dict):
continue
ep_id = int_or_none(ep.get('id'))
ep_url = url_or_none(ep.get('url'))
if ep_id:
e = {
'url': 'videomore:%s' % ep_id,
'id': compat_str(ep_id),
}
elif ep_url:
e = {'url': ep_url}
else:
continue
e.update({
'_type': 'url',
'ie_key': VideomoreIE.ie_key(),
'title': str_or_none(ep.get('title')),
'thumbnail': url_or_none(ep.get('image')),
'duration': parse_duration(ep.get('duration')),
'episode_number': int_or_none(ep.get('number')),
'upload_date': unified_strdate(ep.get('date')),
})
entries.append(e)
if not entries:
entries = [
self.url_result(
'videomore:%s' % video_id, ie=VideomoreIE.ie_key(),
video_id=video_id)
for video_id in orderedSet(re.findall(
r':(?:id|key)=["\'](\d+)["\']', webpage))]
if not entries:
entries = [ entries = [
self.url_result(item) for item in re.findall( self.url_result(item) for item in re.findall(
r'<a[^>]+href="((?:https?:)?//videomore\.ru/%s/[^/]+)"[^>]+class="widget-item-desc"' r'<a[^>]+href="((?:https?:)?//videomore\.ru/%s/[^/]+)"[^>]+class="widget-item-desc"'