Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-08 09:10:09 +01:00
Code Issues Packages Projects Releases Wiki Activity

[einthusan] Improve extraction (Closes #7877)

Browse Source
This commit is contained in:
Sergey M․ 2016-01-01 02:23:03 +06:00
parent 8f7c4f7d2e
commit b26afec81f
1 changed files with 20 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
youtube_dl/extractor/einthusan.py
View File

@ -1,9 +1,12 @@
# 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 ..compat import compat_urlparse
from ..utils import (
remove_start,
sanitized_Request,
)
class EinthusanIE(InfoExtractor): class EinthusanIE(InfoExtractor):
@ -34,30 +37,33 @@ class EinthusanIE(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)
video_title = self._html_search_regex( request = sanitized_Request(url)
r'<h1><a class="movie-title".*?>(.*?)</a></h1>', webpage, 'title') request.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:43.0) Gecko/20100101 Firefox/43.0')
webpage = self._download_webpage(request, video_id)
movieid = self._html_search_regex( title = self._html_search_regex(
r'data-movieid="(.*?)"', webpage, 'movieid') r'<h1><a[^>]+class=["\']movie-title["\'][^>]*>(.+?)</a></h1>',
webpage, 'title')
location = 'Washington' video_id = self._search_regex(
geturl = 'http://cdn.einthusan.com/geturl/%s/hd/%s' % (movieid, location) r'data-movieid=["\'](\d+)', webpage, 'video id', default=video_id)
video_url = self._download_webpage(geturl, video_id)
video_url = self._download_webpage(
'http://cdn.einthusan.com/geturl/%s/hd/London,Washington,Toronto,Dallas,San,Sydney/'
% video_id, video_id)
description = self._html_search_meta('description', webpage) description = self._html_search_meta('description', webpage)
thumbnail = self._html_search_regex( thumbnail = self._html_search_regex(
r'''<a class="movie-cover-wrapper".*?><img src=["'](.*?)["'].*?/></a>''', r'''<a class="movie-cover-wrapper".*?><img src=["'](.*?)["'].*?/></a>''',
webpage, "thumbnail url", fatal=False) webpage, "thumbnail url", fatal=False)
if thumbnail is not None: if thumbnail is not None:
thumbnail = thumbnail.replace('..', 'http://www.einthusan.com') thumbnail = compat_urlparse.urljoin(url, remove_start(thumbnail, '..'))
return { return {
'id': video_id, 'id': video_id,
'title': video_title, 'title': title,
'url': video_url, 'url': video_url,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'description': description, 'description': description,