pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2025-02-04 01:30:12 +09:00
Code Issues Projects Releases Wiki Activity

made changes according to request also I really appreciate help by @dirkf

Browse Source
This commit is contained in:
Ehtisham Sabir 2022-04-01 05:21:57 +05:00
parent 7bf92fd726
commit bf428499a0
1 changed files with 18 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
youtube_dl/extractor/wikimedia.py
View File

@ -1,8 +1,5 @@
from .common import InfoExtractor from .common import InfoExtractor
import re from ..utils import get_element_by_class, compat_urlparse
import requests
import urllib.parse
from ..utils import clean_html
class WikimediaIE(InfoExtractor): class WikimediaIE(InfoExtractor):
@ -29,8 +26,7 @@ class WikimediaIE(InfoExtractor):
'author': 'ZDF/Terra X/Gruppe 5/Luise Wagner, Jonas Sichert, Andreas Hougardy'} 'author': 'ZDF/Terra X/Gruppe 5/Luise Wagner, Jonas Sichert, Andreas Hougardy'}
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')
if not video_id.endswith('.webm'): if not video_id.endswith('.webm'):
raise Exception("invalid video url") raise Exception("invalid video url")
@ -39,32 +35,23 @@ class WikimediaIE(InfoExtractor):
self.report_extraction(video_id) self.report_extraction(video_id)
video_url = self._html_search_regex(r'<source [^>]*src="([^"]+)"', webpage, video_url = self._html_search_regex(r'<source [^>]*src="([^"]+)"', webpage,
u'video URL') u'video URL')
licenze = self._html_search_regex(f"(?<=td>This)(.*)(?=license.)", webpage, u'video license') licenze = self._html_search_regex(r'\bThis\s*(.*?)\s*license\b', webpage, u'video license')
licenze = "This " + licenze + " license." licenze = "This " + licenze + " license."
description = self._html_search_regex(f'(?<=<div class="description mw-content-ltr de" dir="ltr" lang="de">)(' description = get_element_by_class('description', webpage)
f'.*)(?=</div>)', webpage,
u'video description')
author = re.search(r'<td>([^\<]*?)<\/td>', str(webpage)) author = self._html_search_regex(r'<td>([^\<]*?)<\/td>', str(webpage), u"video author")
author = clean_html(author.group(0))
resp = {}
subtitle_url = f'https://commons.wikimedia.org/w/api.php?' \ info = {}
f'action=timedtext&lang=nl&title=File%3A{urllib.parse.quote(video_id)}&trackformat=srt' subtitles = 'https://commons.wikimedia.org/w/api.php?action=timedtext&lang=nl&title=File%3A{}' \
'&trackformat=srt'.format(compat_urlparse.quote_plus(video_id))
subtitles = requests.post(subtitle_url).text info['url'] = video_url
if 'timedtext-notfound' not in subtitles: info['description'] = description
with open(video_id + '.srt', 'w+', encoding='utf') as f: info['ext'] = 'webm'
f.write(subtitles) info['id'] = video_id
else: info['title'] = self._og_search_title(webpage).replace("File:", "")
print("subtitles not found") info['license'] = licenze
info['author'] = author
resp['url'] = video_url info['subtitles'] = {"nl": [{"ext": "srt", "url": subtitles}]}
resp['description'] = description print("ih")
resp['ext'] = 'webm' return info
resp['id'] = video_id
resp['title'] = self._og_search_title(webpage)
resp['license'] = licenze
resp['author'] = author
return [resp]