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.player()
clappr_dict = self._find_clappr_data(webpage, video_id) clappr_dict = self._find_clappr_data(webpage, video_id)
if clappr_dict: if clappr_dict:
info = self._parse_clappr_data(clappr_dict, info = self._parse_clappr_data(clappr_dict, video_id=video_id, base_url=url)
video_id=video_id, base_url=url)
return merge_dicts(info, info_dict) return merge_dicts(info, info_dict)
# Video.js embed # Video.js embed

27
youtube_dl/extractor/vidlox.py
View File

@ -1,10 +1,8 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals 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 from .openload import PhantomJSwrapper
@ -29,8 +27,6 @@ class VidloxIE(InfoExtractor):
'url': 'https://vidlox.me/embed-bs2nk6dgqio1.html', 'url': 'https://vidlox.me/embed-bs2nk6dgqio1.html',
'only_matching': True, 'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -39,37 +35,28 @@ class VidloxIE(InfoExtractor):
phantom = PhantomJSwrapper(self, required_version='2.0') phantom = PhantomJSwrapper(self, required_version='2.0')
# download page for couple simple test # 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: if 'File not found' in webpage:
raise ExtractorError('File not found', expected=True, video_id=video_id) raise ExtractorError('File not found', expected=True, video_id=video_id)
title = None title = None
if 'This video can be watched as embed only.' in webpage: if 'This video can be watched as embed only.' in webpage:
# extract tilte and download embed # extract tilte and download embed
title = self._html_search_regex( title = self._html_search_regex(r'<title[^>]*?>(?P<title>.+?)\s*</title>', webpage, 'title').replace('Watch ', '', 1)
r'<title[^>]*?>(?P<title>.+?)\s*</title>', webpage, 'title').replace('Watch ','',1)
webpage = None webpage = None
page_url = "https://vidlox.me/embed-%s.html" % video_id page_url = "https://vidlox.me/embed-%s.html" % video_id
# execute JS # execute JS
webpage, _ = phantom.get(page_url, webpage, video_id=video_id) webpage, _ = phantom.get(page_url, webpage, video_id=video_id)
# extract player data # extract player data
clappr_dict = self._find_clappr_data(webpage, video_id) clappr_dict = self._find_clappr_data(webpage, video_id)
if not clappr_dict: if not clappr_dict:
raise ExtractorError('Player data not found', raise ExtractorError('Clappr data not found', expected=False, video_id=video_id)
expected=False, video_id=video_id)
# and parse it # and parse it
info_dict = self._parse_clappr_data(clappr_dict, info_dict = self._parse_clappr_data(clappr_dict, video_id=video_id, base_url=page_url)
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['title'] = title or self._html_search_regex(r'<h1[^>]*?>(?P<title>.+?)\s*</h1>', webpage, 'title')
return info_dict return info_dict