[extractor/common] add data, headers and query params to _request_webpage

This commit is contained in:
remitamine 2016-03-10 19:49:13 +01:00
parent e7bd17373d
commit cdfee16818

View file

@ -48,6 +48,7 @@ from ..utils import (
determine_protocol, determine_protocol,
parse_duration, parse_duration,
mimetype2ext, mimetype2ext,
update_url_query,
) )
@ -345,7 +346,7 @@ class InfoExtractor(object):
def IE_NAME(self): def IE_NAME(self):
return compat_str(type(self).__name__[:-2]) return compat_str(type(self).__name__[:-2])
def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers=None, query=None):
""" Returns the response handle """ """ Returns the response handle """
if note is None: if note is None:
self.report_download_webpage(video_id) self.report_download_webpage(video_id)
@ -354,6 +355,12 @@ class InfoExtractor(object):
self.to_screen('%s' % (note,)) self.to_screen('%s' % (note,))
else: else:
self.to_screen('%s: %s' % (video_id, note)) self.to_screen('%s: %s' % (video_id, note))
# data, headers and query params will be ignored for `Request` objects
if isinstance(url_or_request, compat_str):
if query:
url_or_request = update_url_query(url_or_request, query)
if data or headers:
url_or_request = sanitized_Request(url_or_request, data, headers or {})
try: try:
return self._downloader.urlopen(url_or_request) return self._downloader.urlopen(url_or_request)
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
@ -369,13 +376,13 @@ class InfoExtractor(object):
self._downloader.report_warning(errmsg) self._downloader.report_warning(errmsg)
return False return False
def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None): def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None, data=None, headers=None, query=None):
""" Returns a tuple (page content as string, URL handle) """ """ Returns a tuple (page content as string, URL handle) """
# Strip hashes from the URL (#1038) # Strip hashes from the URL (#1038)
if isinstance(url_or_request, (compat_str, str)): if isinstance(url_or_request, (compat_str, str)):
url_or_request = url_or_request.partition('#')[0] url_or_request = url_or_request.partition('#')[0]
urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal) urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query)
if urlh is False: if urlh is False:
assert not fatal assert not fatal
return False return False
@ -462,13 +469,13 @@ class InfoExtractor(object):
return content return content
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None): def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None, data=None, headers=None, query=None):
""" Returns the data of the page as a string """ """ Returns the data of the page as a string """
success = False success = False
try_count = 0 try_count = 0
while success is False: while success is False:
try: try:
res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding) res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding, data=data, headers=headers, query=query)
success = True success = True
except compat_http_client.IncompleteRead as e: except compat_http_client.IncompleteRead as e:
try_count += 1 try_count += 1
@ -483,10 +490,10 @@ class InfoExtractor(object):
def _download_xml(self, url_or_request, video_id, def _download_xml(self, url_or_request, video_id,
note='Downloading XML', errnote='Unable to download XML', note='Downloading XML', errnote='Unable to download XML',
transform_source=None, fatal=True, encoding=None): transform_source=None, fatal=True, encoding=None, data=None, headers=None, query=None):
"""Return the xml as an xml.etree.ElementTree.Element""" """Return the xml as an xml.etree.ElementTree.Element"""
xml_string = self._download_webpage( xml_string = self._download_webpage(
url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding) url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding, data=data, headers=headers, query=query)
if xml_string is False: if xml_string is False:
return xml_string return xml_string
if transform_source: if transform_source:
@ -497,10 +504,10 @@ class InfoExtractor(object):
note='Downloading JSON metadata', note='Downloading JSON metadata',
errnote='Unable to download JSON metadata', errnote='Unable to download JSON metadata',
transform_source=None, transform_source=None,
fatal=True, encoding=None): fatal=True, encoding=None, data=None, headers=None, query=None):
json_string = self._download_webpage( json_string = self._download_webpage(
url_or_request, video_id, note, errnote, fatal=fatal, url_or_request, video_id, note, errnote, fatal=fatal,
encoding=encoding) encoding=encoding, data=data, headers=headers, query=query)
if (not fatal) and json_string is False: if (not fatal) and json_string is False:
return None return None
return self._parse_json( return self._parse_json(