R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

fixed regex searches, capturing display_id, removed download notes, using str_compat

Browse Source
This commit is contained in:
tamas 2018-09-08 22:43:12 +02:00
parent 9184b056d0
commit d548fbd572
1 changed files with 15 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
youtube_dl/extractor/mediaklikk.py
View File

@ -3,7 +3,8 @@ from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_urllib_parse_unquote compat_urllib_parse_unquote,
compat_str
) )
@ -16,6 +17,7 @@ class MediaKlikkIE(InfoExtractor):
'id': '2512015', 'id': '2512015',
'title': 'Az évszakok bűvöletében, Ősz', 'title': 'Az évszakok bűvöletében, Ősz',
'series': 'Az évszakok bűvöletében', 'series': 'Az évszakok bűvöletében',
'display_id': 'az-evszakok-buvoleteben-osz',
'ext': 'mp4' 'ext': 'mp4'
} }
}, },
@ -25,6 +27,7 @@ class MediaKlikkIE(InfoExtractor):
'id': '2523053', 'id': '2523053',
'title': 'Sporthíradó, 350. rész', 'title': 'Sporthíradó, 350. rész',
'series': 'Sporthíradó', 'series': 'Sporthíradó',
'display_id': 'sporthirado-350-resz',
'ext': 'mp4' 'ext': 'mp4'
} }
}, },
@ -32,27 +35,30 @@ class MediaKlikkIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
webpage = self._download_webpage(url, webpage = self._download_webpage(url,
None, None)
note='Fetching page')
pattern = r"mtva_player_manager\.player\(document.getElementById\(.*\),(.*)\);" pattern = r"mtva_player_manager\.player\(document.getElementById\(.*\),\s?(\{.*\}).*\);"
info_json = self._html_search_regex(pattern, webpage, 'info_json') info_json = self._html_search_regex(pattern, webpage, 'info_json')
info_meta = self._parse_json(compat_urllib_parse_unquote(info_json), info_meta = self._parse_json(compat_urllib_parse_unquote(info_json),
None) None)
video_id = str(info_meta['contentId']) pattern = r"https?://(?:www\.)?mediaklikk\.hu/video/([a-z\-0-9]+)/?"
if type(video_id) == bytes: display_id = self._search_regex(pattern, url, 'display_id')
video_id = video_id.decode('utf-8') video_id = compat_str(info_meta['contentId'])
info_ret = { info_ret = {
'_type': 'video', '_type': 'video',
'title': info_meta.get('title') or self._og_search_title(webpage), 'title': info_meta.get('title') or self._og_search_title(webpage),
'ext': 'mp4', 'ext': 'mp4',
'display_id': display_id,
'id': video_id 'id': video_id
} }
if 'series' in info_meta: if 'series' in info_meta:
info_ret['series'] = info_meta['series'] info_ret['series'] = info_meta['series']
info_meta['video'] = info_meta['token'] info_meta['video'] = info_meta['token']
del info_meta['token'] del info_meta['token']
playerpage = self._download_webpage('https://player.mediaklikk.hu/playernew/player.php', video_id, note='Downloading player page', query=info_meta) playerpage = self._download_webpage('https://player.mediaklikk.hu/playernew/player.php',
pattern = r"\"file\": \"(.*)\"," video_id,
query=info_meta)
pattern = r"\"file\": \"(\\/\\/.*playlist\.m3u8)\","
playlist_url = 'https:' + compat_urllib_parse_unquote( playlist_url = 'https:' + compat_urllib_parse_unquote(
self._html_search_regex(pattern, playerpage, 'playlist_url'))\ self._html_search_regex(pattern, playerpage, 'playlist_url'))\
.replace('\\/', '/') .replace('\\/', '/')