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

Add support for Clapper library and add extractor Vidlox

Browse Source
This commit is contained in:
bato3 2018-07-12 17:55:19 +02:00
parent 9dc48d44b5
commit 99d88a0b5c
2 changed files with 8 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
youtube_dl/extractor/generic.py
View File

@ -3131,8 +3131,7 @@ class GenericIE(InfoExtractor):
# Clappr.player()
clappr_dict = self._find_clappr_data(webpage, video_id)
if clappr_dict:
info = self._parse_clappr_data(clappr_dict,
video_id=video_id, base_url=url)
info = self._parse_clappr_data(clappr_dict, video_id=video_id, base_url=url)
return merge_dicts(info, info_dict)
# Video.js embed

27
youtube_dl/extractor/vidlox.py
View File

@ -1,10 +1,8 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from ..utils import ExtractorError
from .common import InfoExtractor
from ..utils import ExtractorError
from .common import InfoExtractor
from .openload import PhantomJSwrapper
@ -30,8 +28,6 @@ class VidloxIE(InfoExtractor):
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
@ -39,37 +35,28 @@ class VidloxIE(InfoExtractor):
phantom = PhantomJSwrapper(self, required_version='2.0')
# download page for couple simple test
webpage = self._download_webpage(page_url, video_id).replace("\n","").replace("\t","")
webpage = self._download_webpage(page_url, video_id).replace("\n", "").replace("\t", "")
if 'File not found' in webpage:
raise ExtractorError('File not found', expected=True, video_id=video_id)
title = None
if 'This video can be watched as embed only.' in webpage:
# extract tilte and download embed
title = self._html_search_regex(
r'<title[^>]*?>(?P<title>.+?)\s*</title>', webpage, 'title').replace('Watch ','',1)
title = self._html_search_regex(r'<title[^>]*?>(?P<title>.+?)\s*</title>', webpage, 'title').replace('Watch ', '', 1)
webpage = None
page_url = "https://vidlox.me/embed-%s.html" % video_id
# execute JS
webpage, _ = phantom.get(page_url, webpage, video_id=video_id)
# extract player data
clappr_dict = self._find_clappr_data(webpage, video_id)
if not clappr_dict:
raise ExtractorError('Player data not found',
expected=False, video_id=video_id)
raise ExtractorError('Clappr data not found', expected=False, video_id=video_id)
# and parse it
info_dict = self._parse_clappr_data(clappr_dict,
video_id=video_id, base_url=page_url)
info_dict['title'] = title or self._html_search_regex(
r'<h1[^>]*?>(?P<title>.+?)\s*</h1>', webpage, 'title')
info_dict = self._parse_clappr_data(clappr_dict, video_id=video_id, base_url=page_url)
info_dict['title'] = title or self._html_search_regex(r'<h1[^>]*?>(?P<title>.+?)\s*</h1>', webpage, 'title')
return info_dict