[malltv] Add extractor (closes #18058)

This commit is contained in:
Ales Jirasek 2018-10-10 23:47:21 +02:00 committed by Sergey M․
parent 49bd993fd9
commit 22f5f5c6fc
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
5 changed files with 63 additions and 2 deletions

View File

@ -61,6 +61,7 @@ class TestInfoExtractor(unittest.TestCase):
<meta content='Foo' property=og:foobar> <meta content='Foo' property=og:foobar>
<meta name="og:test1" content='foo > < bar'/> <meta name="og:test1" content='foo > < bar'/>
<meta name="og:test2" content="foo >//< bar"/> <meta name="og:test2" content="foo >//< bar"/>
<meta property=og-test3 content='Ill-formatted opengraph'/>
''' '''
self.assertEqual(ie._og_search_title(html), 'Foo') self.assertEqual(ie._og_search_title(html), 'Foo')
self.assertEqual(ie._og_search_description(html), 'Some video\'s description ') self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
@ -69,6 +70,7 @@ class TestInfoExtractor(unittest.TestCase):
self.assertEqual(ie._og_search_property('foobar', html), 'Foo') self.assertEqual(ie._og_search_property('foobar', html), 'Foo')
self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar') self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar')
self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar') self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar')
self.assertEqual(ie._og_search_property('test3', html), 'Ill-formatted opengraph')
self.assertEqual(ie._og_search_property(('test0', 'test1'), html), 'foo > < bar') self.assertEqual(ie._og_search_property(('test0', 'test1'), html), 'foo > < bar')
self.assertRaises(RegexNotFoundError, ie._og_search_property, 'test0', html, None, fatal=True) self.assertRaises(RegexNotFoundError, ie._og_search_property, 'test0', html, None, fatal=True)
self.assertRaises(RegexNotFoundError, ie._og_search_property, ('test0', 'test00'), html, None, fatal=True) self.assertRaises(RegexNotFoundError, ie._og_search_property, ('test0', 'test00'), html, None, fatal=True)

View File

@ -1058,7 +1058,7 @@ class InfoExtractor(object):
@staticmethod @staticmethod
def _og_regexes(prop): def _og_regexes(prop):
content_re = r'content=(?:"([^"]+?)"|\'([^\']+?)\'|\s*([^\s"\'=<>`]+?))' content_re = r'content=(?:"([^"]+?)"|\'([^\']+?)\'|\s*([^\s"\'=<>`]+?))'
property_re = (r'(?:name|property)=(?:\'og:%(prop)s\'|"og:%(prop)s"|\s*og:%(prop)s\b)' property_re = (r'(?:name|property)=(?:\'og[:-]%(prop)s\'|"og[:-]%(prop)s"|\s*og[:-]%(prop)s\b)'
% {'prop': re.escape(prop)}) % {'prop': re.escape(prop)})
template = r'<meta[^>]+?%s[^>]+?%s' template = r'<meta[^>]+?%s[^>]+?%s'
return [ return [

View File

@ -619,6 +619,7 @@ from .mailru import (
MailRuMusicSearchIE, MailRuMusicSearchIE,
) )
from .makertv import MakerTVIE from .makertv import MakerTVIE
from .malltv import MallTVIE
from .mangomolo import ( from .mangomolo import (
MangomoloVideoIE, MangomoloVideoIE,
MangomoloLiveIE, MangomoloLiveIE,

View File

@ -0,0 +1,58 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import parse_duration, merge_dicts
class MallTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?mall\.tv/(?:.+/)?(?P<id>.+)(?:\?.*$|$)'
_TESTS = [
{
'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
'md5': '9ced0de056534410837077e23bfba796',
'info_dict': {
'id': 't0zzt0',
'ext': 'mp4',
'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?',
'description': 'Pokud někdo hospodaří s penězmi daňových poplatníků, pak logicky chceme vědět, jak s nimi nakládá. Objem dotací pro neziskovky roste, ale opravdu jsou tyto organizace „pijavice", jak o nich hovoří And',
'upload_date': '20181007',
'timestamp': 1538870400
}
},
{
'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
'md5': '9ced0de056534410837077e23bfba796',
'only_matching': 1,
'info_dict': {
'id': 't0zzt0',
'ext': 'mp4',
'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?',
'description': 'Pokud někdo hospodaří s penězmi daňových poplatníků, pak logicky chceme vědět, jak s nimi nakládá. Objem dotací pro neziskovky roste, ale opravdu jsou tyto organizace „pijavice", jak o nich hovoří And',
'upload_date': '20181007',
'timestamp': 1538870400
}
}
]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
src_id_regex = r'(?P<src><source src=([\"\'])?.+?/(?P<id>\w{6,}?)/index)(?P<after>\1?[^>]*?>)'
video_id = self._search_regex(src_id_regex, webpage, 'ID',
group='id')
info = self._search_json_ld(webpage, video_id, default={})
html = re.sub(src_id_regex, r'\g<src>.m3u8\g<after>', webpage)
media = self._parse_html5_media_entries(url, html, video_id)
thumbnail = info.get('thumbnail', self._og_search_thumbnail(webpage))
duration = parse_duration(info.get('duration'))
result = {
'id': video_id,
'title': info.get('title', self._og_search_title(webpage)),
'description': self._og_search_description(webpage)
}
result.update({'thumbnail': thumbnail})
result.update({'duration': duration})
return merge_dicts(media[0], info, result)

View File

@ -184,7 +184,7 @@ DATE_FORMATS_MONTH_FIRST.extend([
]) ])
PACKED_CODES_RE = r"}\('(.+)',(\d+),(\d+),'([^']+)'\.split\('\|'\)" PACKED_CODES_RE = r"}\('(.+)',(\d+),(\d+),'([^']+)'\.split\('\|'\)"
JSON_LD_RE = r'(?is)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>' JSON_LD_RE = r'(?is)<script[^>]+type=(["\']?)application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>'
def preferredencoding(): def preferredencoding():