mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-05 07:53:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

clean code

Browse source
This commit is contained in:
EGA-SUPREMO 2024-05-03 07:35:03 -04:00
parent 16d3268cf9
commit 3997c6d84b
1 changed files with 8 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
yt_dlp/extractor/fyptt.py
View file

@ -33,27 +33,24 @@ class FYPTTIE(InfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
def _download_webpage_handle(self, *args, **kwargs):
headers = kwargs.get('headers', {}).copy()
headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36'
kwargs['headers'] = headers
return super(FYPTTIE, self)._download_webpage_handle(
*args, **kwargs)
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
formats = [] formats = []
# format_url = self._html_search_regex(r'<span">(.+?)</span>', webpage, 'title')
format_url = self._html_search_regex(r'"embedURL":"([^"]+)"', webpage, 'video URL') format_url = self._html_search_regex(r'"embedURL":"([^"]+)"', webpage, 'video URL')
# Remove invalid characters using regex
format_url = re.sub(r'\\', '', format_url) format_url = re.sub(r'\\', '', format_url)
print("format_url")
print(format_url)
webpage_video = self._download_webpage(format_url, video_id) webpage_video = self._download_webpage(format_url, video_id)
# format_url = self._html_search_regex(r'<source\s+src="(.+?)"\s+type', webpage, 'format_url')
match = re.search(r'<source\s+src="(.+?)"\s+type', webpage_video) match = re.search(r'<source\s+src="(.+?)"\s+type', webpage_video)
format_url = match.group(1) format_url = match.group(1)
print(match)
formats.append({ formats.append({
'url': format_url, 'url': format_url,
'format_id': 'default', 'format_id': 'default',
@ -61,7 +58,6 @@ def _real_extract(self, url):
title = self._html_search_regex(r'<span class="fl-heading-text">(.+?)</span>', webpage, 'title') title = self._html_search_regex(r'<span class="fl-heading-text">(.+?)</span>', webpage, 'title')
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,