Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-12 14:26:49 +01:00
Code Issues Packages Projects Releases Wiki Activity

New debug option --write-pages

Browse Source
This commit is contained in:
Philipp Hagemeister 2013-10-28 10:44:02 +01:00
parent c19f7764a5
commit d41e6efc85
2 changed files with 16 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
youtube_dl/__init__.py
View File

@ -316,6 +316,9 @@ def _hide_login_info(opts):
verbosity.add_option('--dump-intermediate-pages',
action='store_true', dest='dump_intermediate_pages', default=False,
help='print downloaded pages to debug problems(very verbose)')
verbosity.add_option('--write-pages',
action='store_true', dest='write_pages', default=False,
help='Write downloaded pages to files in the current directory')
verbosity.add_option('--youtube-print-sig-code',
action='store_true', dest='youtube_print_sig_code', default=False,
help=optparse.SUPPRESS_HELP)
@ -652,6 +655,7 @@ def _real_main(argv=None):
'prefer_free_formats': opts.prefer_free_formats,
'verbose': opts.verbose,
'dump_intermediate_pages': opts.dump_intermediate_pages,
'write_pages': opts.write_pages,
'test': opts.test,
'keepvideo': opts.keepvideo,
'min_filesize': opts.min_filesize,

12
youtube_dl/extractor/common.py
View File

@ -15,6 +15,7 @@
compiled_regex_type,
ExtractorError,
RegexNotFoundError,
sanitize_filename,
unescapeHTML,
)
@ -182,6 +183,17 @@ def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=
self.to_screen(u'Dumping request to ' + url)
dump = base64.b64encode(webpage_bytes).decode('ascii')
self._downloader.to_screen(dump)
if self._downloader.params.get('write_pages', False):
try:
url = url_or_request.get_full_url()
except AttributeError:
url = url_or_request
raw_filename = ('%s_%s.dump' % (video_id, url))
filename = sanitize_filename(raw_filename, restricted=True)
self.to_screen(u'Saving request to ' + filename)
with open(filename, 'wb') as outf:
outf.write(webpage_bytes)
content = webpage_bytes.decode(encoding, 'replace')
return (content, urlh)