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

[kotnrtube] Improve metadata extraction

Browse Source
This commit is contained in:
Déstin Reed 2016-10-02 00:00:03 +02:00
parent e295618f9e
commit 5867abd840
1 changed files with 16 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
youtube_dl/extractor/kontrtube.py
View File

@ -1,4 +1,4 @@
# encoding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
@ -6,12 +6,12 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
js_to_json,
parse_duration, parse_duration,
) )
class KontrTubeIE(InfoExtractor): class KontrTubeIE(InfoExtractor):
IE_NAME = 'kontrtube'
IE_DESC = 'KontrTube.ru - Труба зовёт' IE_DESC = 'KontrTube.ru - Труба зовёт'
_VALID_URL = r'https?://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/(?P<display_id>[^/]+)/' _VALID_URL = r'https?://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/(?P<display_id>[^/]+)/'
@ -31,16 +31,25 @@ class KontrTubeIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id, display_id = mobj.groups()
display_id = mobj.group('display_id')
webpage = self._download_webpage( webpage = self._download_webpage(url, display_id)
url, display_id, 'Downloading page')
video_data = self._parse_json(
self._search_regex(
r'var\s+flashvars\s*=\s*({[^}]+});', webpage, 'video data', fatal=False),
video_id, transform_source=js_to_json)
video_url = self._search_regex( video_url = self._search_regex(
r"video_url\s*:\s*'(.+?)/?',", webpage, 'video URL') r"video_url\s*:\s*'(.+?)/?',", webpage, 'video URL', fatal=False)
thumbnail = self._search_regex( thumbnail = self._search_regex(
r"preview_url\s*:\s*'(.+?)/?',", webpage, 'thumbnail', fatal=False) r"preview_url\s*:\s*'(.+?)/?',", webpage, 'thumbnail', fatal=False)
if not video_url:
video_url = video_data['video_url']
if not thumbnail:
thumbnail = video_data.get('preview_url')
title = self._html_search_regex( title = self._html_search_regex(
r'(?s)<h2>(.+?)</h2>', webpage, 'title') r'(?s)<h2>(.+?)</h2>', webpage, 'title')
description = self._html_search_meta( description = self._html_search_meta(