mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2026-02-05 13:37:03 +00:00
Code Issues Projects Releases Wiki Activity

[cleanup] Misc cleanup

Browse Source
This commit is contained in:
pukkandan
2022-06-28 10:40:54 +05:30
parent 47046464fa
commit ae61d108dd
10 changed files with 65 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
yt_dlp/extractor/generic.py
View File

@@ -2825,12 +2825,22 @@ class GenericIE(InfoExtractor):
new_url, {'force_videoid': force_videoid})
return self.url_result(new_url)
def request_webpage():
request = sanitized_Request(url)
# Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
# making it impossible to download only chunk of the file (yet we need only 512kB to
# test whether it's HTML or not). According to yt-dlp default Accept-Encoding
# that will always result in downloading the whole file that is not desirable.
# Therefore for extraction pass we have to override Accept-Encoding to any in order
# to accept raw bytes and being able to download only a chunk.
# It may probably better to solve this by checking Content-Type for application/octet-stream
# after HEAD request finishes, but not sure if we can rely on this.
request.add_header('Accept-Encoding', '*')
return self._request_webpage(request, video_id)
full_response = None
if head_response is False:
request = sanitized_Request(url)
request.add_header('Accept-Encoding', '*')
full_response = self._request_webpage(request, video_id)
head_response = full_response
head_response = full_response = request_webpage()
info_dict = {
'id': video_id,
@@ -2868,19 +2878,7 @@ class GenericIE(InfoExtractor):
self.report_warning(
'%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
if not full_response:
request = sanitized_Request(url)
# Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
# making it impossible to download only chunk of the file (yet we need only 512kB to
# test whether it's HTML or not). According to yt-dlp default Accept-Encoding
# that will always result in downloading the whole file that is not desirable.
# Therefore for extraction pass we have to override Accept-Encoding to any in order
# to accept raw bytes and being able to download only a chunk.
# It may probably better to solve this by checking Content-Type for application/octet-stream
# after HEAD request finishes, but not sure if we can rely on this.
request.add_header('Accept-Encoding', '*')
full_response = self._request_webpage(request, video_id)
full_response = full_response or request_webpage()
first_bytes = full_response.read(512)
# Is it an M3U playlist?

9
yt_dlp/extractor/youtube.py
View File

@@ -2467,6 +2467,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
assert os.path.basename(func_id) == func_id
self.write_debug(f'Extracting signature function {func_id}')
cache_spec = self.cache.load('youtube-sigfuncs', func_id)
if cache_spec is not None:
return lambda s: ''.join(s[i] for i in cache_spec)
@@ -2714,10 +2715,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
@classmethod
def extract_id(cls, url):
mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
if mobj is None:
raise ExtractorError('Invalid URL: %s' % url)
return mobj.group('id')
video_id = cls.get_temp_id(url)
if not video_id:
raise ExtractorError(f'Invalid URL: {url}')
return video_id
def _extract_chapters_from_json(self, data, duration):
chapter_list = traverse_obj(