fenix
/
ytdl-nightly
mirror of https://github.com/ytdl-org/ytdl-nightly.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[goshgay] Fix title extraction and modernize 

Also remove width and height as they are not of the actual video.
This commit is contained in:
Naglis Jonaitis 2014-11-06 01:19:20 +02:00
parent 37aab27808
commit 5d63b0aa93
1 changed files with 14 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
youtube_dl/extractor/goshgay.py
View File

@ -1,15 +1,11 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
compat_urlparse, compat_urlparse,
str_to_int,
ExtractorError, ExtractorError,
) )
import json
class GoshgayIE(InfoExtractor): class GoshgayIE(InfoExtractor):
@ -27,36 +23,27 @@ class GoshgayIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._search_regex(r'class="video-title"><h1>(.+?)<', webpage, 'title') title = self._og_search_title(webpage)
thumbnail = self._og_search_thumbnail(webpage)
family_friendly = self._html_search_meta(
'isFamilyFriendly', webpage, default='false')
config_url = self._search_regex(
r"'config'\s*:\s*'([^']+)'", webpage, 'config URL')
player_config = self._search_regex( config = self._download_xml(
r'(?s)jwplayer\("player"\)\.setup\(({.+?})\)', webpage, 'config settings') config_url, video_id, 'Downloading player config XML')
player_vars = json.loads(player_config.replace("'", '"'))
width = str_to_int(player_vars.get('width'))
height = str_to_int(player_vars.get('height'))
config_uri = player_vars.get('config')
if config_uri is None: if config is None:
raise ExtractorError('Missing config URI')
node = self._download_xml(config_uri, video_id, 'Downloading player config XML',
errnote='Unable to download XML')
if node is None:
raise ExtractorError('Missing config XML') raise ExtractorError('Missing config XML')
if node.tag != 'config': if config.tag != 'config':
raise ExtractorError('Missing config attribute') raise ExtractorError('Missing config attribute')
fns = node.findall('file') fns = config.findall('file')
imgs = node.findall('image') if len(fns) < 1:
if len(fns) != 1:
raise ExtractorError('Missing media URI') raise ExtractorError('Missing media URI')
video_url = fns[0].text video_url = fns[0].text
if len(imgs) < 1:
thumbnail = None
else:
thumbnail = imgs[0].text
url_comp = compat_urlparse.urlparse(url) url_comp = compat_urlparse.urlparse(url)
ref = "%s://%s%s" % (url_comp[0], url_comp[1], url_comp[2]) ref = "%s://%s%s" % (url_comp[0], url_comp[1], url_comp[2])
@ -65,9 +52,7 @@ class GoshgayIE(InfoExtractor):
'id': video_id, 'id': video_id,
'url': video_url, 'url': video_url,
'title': title, 'title': title,
'width': width,
'height': height,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'http_referer': ref, 'http_referer': ref,
'age_limit': 18, 'age_limit': 0 if family_friendly == 'true' else 18,
} }