[extractor] Add dev option --load-pages

This commit is contained in:
pukkandan 2022-06-01 02:03:22 +05:30
parent 617f658b7e
commit f95b9dee45
No known key found for this signature in database
GPG Key ID: 7EEE9E1E817D0A39
4 changed files with 54 additions and 36 deletions

View File

@ -2022,6 +2022,7 @@ #### Developer options
These options are not intended to be used by the end-user These options are not intended to be used by the end-user
--test Download only part of video for testing extractors --test Download only part of video for testing extractors
--load-pages Load pages dumped by --write-pages
--youtube-print-sig-code For testing youtube signatures --youtube-print-sig-code For testing youtube signatures
--allow-unplayable-formats List unplayable formats also --allow-unplayable-formats List unplayable formats also
--no-allow-unplayable-formats Default --no-allow-unplayable-formats Default

View File

@ -758,6 +758,7 @@ def parse_options(argv=None):
'verbose': opts.verbose, 'verbose': opts.verbose,
'dump_intermediate_pages': opts.dump_intermediate_pages, 'dump_intermediate_pages': opts.dump_intermediate_pages,
'write_pages': opts.write_pages, 'write_pages': opts.write_pages,
'load_pages': opts.load_pages,
'test': opts.test, 'test': opts.test,
'keepvideo': opts.keepvideo, 'keepvideo': opts.keepvideo,
'min_filesize': opts.min_filesize, 'min_filesize': opts.min_filesize,

View File

@ -75,7 +75,6 @@
unified_strdate, unified_strdate,
unified_timestamp, unified_timestamp,
update_Request, update_Request,
update_url_query,
url_basename, url_basename,
url_or_none, url_or_none,
urljoin, urljoin,
@ -724,6 +723,11 @@ def __can_accept_status_code(err, expected_status):
else: else:
return err.code in variadic(expected_status) return err.code in variadic(expected_status)
def _create_request(self, url_or_request, data=None, headers={}, query={}):
if not isinstance(url_or_request, compat_urllib_request.Request):
url_or_request = sanitized_Request(url_or_request)
return update_Request(url_or_request, data=data, headers=headers, query=query)
def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers={}, query={}, expected_status=None): def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers={}, query={}, expected_status=None):
""" """
Return the response handle. Return the response handle.
@ -755,16 +759,8 @@ def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fa
if 'X-Forwarded-For' not in headers: if 'X-Forwarded-For' not in headers:
headers['X-Forwarded-For'] = self._x_forwarded_for_ip headers['X-Forwarded-For'] = self._x_forwarded_for_ip
if isinstance(url_or_request, compat_urllib_request.Request):
url_or_request = update_Request(
url_or_request, data=data, headers=headers, query=query)
else:
if query:
url_or_request = update_url_query(url_or_request, query)
if data is not None or headers:
url_or_request = sanitized_Request(url_or_request, data, headers)
try: try:
return self._downloader.urlopen(url_or_request) return self._downloader.urlopen(self._create_request(url_or_request, data, headers, query))
except network_exceptions as err: except network_exceptions as err:
if isinstance(err, compat_urllib_error.HTTPError): if isinstance(err, compat_urllib_error.HTTPError):
if self.__can_accept_status_code(err, expected_status): if self.__can_accept_status_code(err, expected_status):
@ -876,40 +872,44 @@ def __check_blocked(self, content):
'Visit http://blocklist.rkn.gov.ru/ for a block reason.', 'Visit http://blocklist.rkn.gov.ru/ for a block reason.',
expected=True) expected=True)
def _request_dump_filename(self, url, video_id):
basen = f'{video_id}_{url}'
trim_length = self.get_param('trim_file_name') or 240
if len(basen) > trim_length:
h = '___' + hashlib.md5(basen.encode('utf-8')).hexdigest()
basen = basen[:trim_length - len(h)] + h
filename = sanitize_filename(f'{basen}.dump', restricted=True)
# Working around MAX_PATH limitation on Windows (see
# http://msdn.microsoft.com/en-us/library/windows/desktop/aa365247(v=vs.85).aspx)
if compat_os_name == 'nt':
absfilepath = os.path.abspath(filename)
if len(absfilepath) > 259:
filename = fR'\\?\{absfilepath}'
return filename
def __decode_webpage(self, webpage_bytes, encoding, headers):
if not encoding:
encoding = self._guess_encoding_from_content(headers.get('Content-Type', ''), webpage_bytes)
try:
return webpage_bytes.decode(encoding, 'replace')
except LookupError:
return webpage_bytes.decode('utf-8', 'replace')
def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None, encoding=None): def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None, encoding=None):
content_type = urlh.headers.get('Content-Type', '')
webpage_bytes = urlh.read() webpage_bytes = urlh.read()
if prefix is not None: if prefix is not None:
webpage_bytes = prefix + webpage_bytes webpage_bytes = prefix + webpage_bytes
if not encoding:
encoding = self._guess_encoding_from_content(content_type, webpage_bytes)
if self.get_param('dump_intermediate_pages', False): if self.get_param('dump_intermediate_pages', False):
self.to_screen('Dumping request to ' + urlh.geturl()) self.to_screen('Dumping request to ' + urlh.geturl())
dump = base64.b64encode(webpage_bytes).decode('ascii') dump = base64.b64encode(webpage_bytes).decode('ascii')
self._downloader.to_screen(dump) self._downloader.to_screen(dump)
if self.get_param('write_pages', False): if self.get_param('write_pages'):
basen = f'{video_id}_{urlh.geturl()}' filename = self._request_dump_filename(video_id, urlh.geturl())
trim_length = self.get_param('trim_file_name') or 240 self.to_screen(f'Saving request to {filename}')
if len(basen) > trim_length:
h = '___' + hashlib.md5(basen.encode('utf-8')).hexdigest()
basen = basen[:trim_length - len(h)] + h
raw_filename = basen + '.dump'
filename = sanitize_filename(raw_filename, restricted=True)
self.to_screen('Saving request to ' + filename)
# Working around MAX_PATH limitation on Windows (see
# http://msdn.microsoft.com/en-us/library/windows/desktop/aa365247(v=vs.85).aspx)
if compat_os_name == 'nt':
absfilepath = os.path.abspath(filename)
if len(absfilepath) > 259:
filename = '\\\\?\\' + absfilepath
with open(filename, 'wb') as outf: with open(filename, 'wb') as outf:
outf.write(webpage_bytes) outf.write(webpage_bytes)
try: content = self.__decode_webpage(webpage_bytes, encoding, urlh.headers)
content = webpage_bytes.decode(encoding, 'replace')
except LookupError:
content = webpage_bytes.decode('utf-8', 'replace')
self.__check_blocked(content) self.__check_blocked(content)
return content return content
@ -967,9 +967,21 @@ def download_handle(self, url_or_request, video_id, note=note, errnote=errnote,
content, urlh = res content, urlh = res
return parse(self, content, video_id, transform_source, fatal), urlh return parse(self, content, video_id, transform_source, fatal), urlh
def download_content( def download_content(self, url_or_request, video_id, note=note, errnote=errnote, transform_source=None,
self, url_or_request, video_id, note=note, errnote=errnote, transform_source=None, *args, **kwargs): fatal=True, encoding=None, data=None, headers={}, query={}, *args, **kwargs):
args = [url_or_request, video_id, note, errnote, transform_source, *args] if self.get_param('load_pages'):
url_or_request = self._create_request(url_or_request, data, headers, query)
filename = self._request_dump_filename(url_or_request.full_url, video_id)
self.to_screen(f'Loading request from {filename}')
try:
with open(filename, 'rb') as dumpf:
webpage_bytes = dumpf.read()
except OSError as e:
self.report_warning(f'Unable to load request from disk: {e}')
else:
content = self.__decode_webpage(webpage_bytes, encoding, url_or_request.headers)
return parse(self, content, video_id, transform_source, fatal)
args = [url_or_request, video_id, note, errnote, transform_source, fatal, encoding, data, headers, query, *args]
if parser is None: if parser is None:
args.pop(4) # transform_source args.pop(4) # transform_source
# The method is fetched by name so subclasses can override _download_..._handle # The method is fetched by name so subclasses can override _download_..._handle

View File

@ -1154,6 +1154,10 @@ def _alias_callback(option, opt_str, value, parser, opts, nargs):
'--write-pages', '--write-pages',
action='store_true', dest='write_pages', default=False, action='store_true', dest='write_pages', default=False,
help='Write downloaded intermediary pages to files in the current directory to debug problems') help='Write downloaded intermediary pages to files in the current directory to debug problems')
verbosity.add_option(
'--load-pages',
action='store_true', dest='load_pages', default=False,
help=optparse.SUPPRESS_HELP)
verbosity.add_option( verbosity.add_option(
'--youtube-print-sig-code', '--youtube-print-sig-code',
action='store_true', dest='youtube_print_sig_code', default=False, action='store_true', dest='youtube_print_sig_code', default=False,