def rewrite(self, url_info):
if url_info.scheme not in ('http', 'https'):
return url_info
if self._session_id_enabled:
url = '{scheme}://{authority}{path}?{query}#{fragment}'.format(
scheme=url_info.scheme,
authority=url_info.authority,
path=strip_path_session_id(url_info.path),
query=strip_query_session_id(url_info.query),
fragment=url_info.fragment,
)
url_info = parse_url_or_log(url) or url_info
if self._hash_fragment_enabled and url_info.fragment.startswith('!'):
if url_info.query:
url = '{}&_escaped_fragment_={}'.format(
url_info.url, url_info.fragment[1:])
else:
url = '{}?_escaped_fragment_={}'.format(
url_info.url, url_info.fragment[1:])
url_info = parse_url_or_log(url) or url_info
return url_info
def rewrite(self, url_info: URLInfo) -> URLInfo:
'''Rewrite the given URL.'''
if url_info.scheme not in ('http', 'https'):
return url_info
if self._session_id_enabled:
url = '{scheme}://{authority}{path}?{query}#{fragment}'.format(
scheme=url_info.scheme,
authority=url_info.authority,
path=strip_path_session_id(url_info.path),
query=strip_query_session_id(url_info.query),
fragment=url_info.fragment,
)
url_info = parse_url_or_log(url) or url_info
if self._hash_fragment_enabled and url_info.fragment.startswith('!'):
if url_info.query:
url = '{}&_escaped_fragment_={}'.format(url_info.url,
url_info.fragment[1:])
else:
url = '{}?_escaped_fragment_={}'.format(url_info.url,
url_info.fragment[1:])
url_info = parse_url_or_log(url) or url_info
return url_info
def check_in(self, url, new_status, *args, **kwargs):
if new_status == Status.error and self.is_hook_connected('queued_url'):
self._queue_counter += 1
url_info = parse_url_or_log(url)
if url_info:
self.call_hook('queued_url', url_info)
return self.url_table.check_in(url, new_status, *args, **kwargs)
def check_in(self, url, new_status, increment_try_count=True,
url_result=None):
if new_status == Status.error:
self._queue_counter += 1
url_info = parse_url_or_log(url)
if url_info:
self.event_dispatcher.notify(PluginFunctions.queued_url, url_info)
return self.url_table.check_in(url, new_status, increment_try_count=increment_try_count, url_result=url_result)
def add_many(self, urls):
added_urls = tuple(self.url_table.add_many(urls))
for url in added_urls:
url_info = parse_url_or_log(url)
if url_info:
self._queue_counter += 1
self.event_dispatcher.notify(PluginFunctions.queued_url, url_info)
return added_urls
def add_many(self, urls, **kwargs):
added_urls = tuple(self.url_table.add_many(urls, **kwargs))
if self.is_hook_connected('queued_url'):
for url in added_urls:
url_info = parse_url_or_log(url)
if url_info:
self._queue_counter += 1
self.call_hook('queued_url', url_info)
return added_urls
def add_many(self, urls):
added_urls = tuple(self.url_table.add_many(urls))
for url in added_urls:
url_info = parse_url_or_log(url)
if url_info:
self._queue_counter += 1
self.event_dispatcher.notify(PluginFunctions.queued_url,
url_info)
return added_urls
def add_url(self, url: str, url_properites: Optional[URLProperties]=None,
url_data: Optional[URLData]=None):
url_info = parse_url_or_log(url)
if not url_info:
return
url_properties = url_properites or URLProperties()
url_data = url_data or URLData()
add_url_info = AddURLInfo(url, url_properties, url_data)
self._add_url_batch.append(add_url_info)
if len(self._add_url_batch) >= 1000:
self.app_session.factory['URLTable'].add_many(self._add_url_batch)
self._add_url_batch.clear()
def check_in(self,
url,
new_status,
increment_try_count=True,
url_result=None):
if new_status == Status.error:
self._queue_counter += 1
url_info = parse_url_or_log(url)
if url_info:
self.event_dispatcher.notify(PluginFunctions.queued_url,
url_info)
return self.url_table.check_in(url,
new_status,
increment_try_count=increment_try_count,
url_result=url_result)
def _add_listing_links(self, response):
'''Add links from file listing response.'''
base_url = response.request.url_info.url
dir_urls_to_add = set()
file_urls_to_add = set()
if self._glob_pattern:
level = self._url_item.url_record.level
else:
level = None
for file_entry in response.files:
if self._glob_pattern and \
not fnmatch.fnmatchcase(file_entry.name, self._glob_pattern):
continue
if file_entry.type == 'dir':
linked_url = urljoin_safe(base_url, file_entry.name + '/')
elif file_entry.type in ('file', 'symlink', None):
if not self._processor.fetch_params.retr_symlinks and \
file_entry.type == 'symlink':
self._make_symlink(file_entry.name, file_entry.dest)
linked_url = None
else:
linked_url = urljoin_safe(base_url, file_entry.name)
else:
linked_url = None
if linked_url:
linked_url_info = parse_url_or_log(linked_url)
if linked_url_info:
linked_url_record = self._url_item.child_url_record(linked_url_info, level=level)
verdict = self._fetch_rule.check_ftp_request(
linked_url_info, linked_url_record)[0]
if verdict:
if linked_url_info.path.endswith('/'):
dir_urls_to_add.add(linked_url_info.url)
else:
file_urls_to_add.add(linked_url_info.url)
self._url_item.add_child_urls(dir_urls_to_add, link_type=LinkType.directory)
self._url_item.add_child_urls(file_urls_to_add, link_type=LinkType.file, level=level)
def _add_hooked_url(self, url_item, new_url_dict):
'''Process the ``dict`` from the script and add the URLs.'''
url = new_url_dict['url']
link_type = new_url_dict.get('link_type')
inline = new_url_dict.get('inline')
post_data = new_url_dict.get('post_data')
replace = new_url_dict.get('replace')
assert url
url_info = parse_url_or_log(url)
if not url_info:
return
kwargs = dict(link_type=link_type, post_data=post_data)
if replace:
url_item.url_table.remove_one(url)
url_item.add_child_url(url_info.url, inline=inline, **kwargs)
def _add_hooked_url(self, url_item, new_url_dict):
'''Process the ``dict`` from the script and add the URLs.'''
url = new_url_dict['url']
link_type = new_url_dict.get('link_type')
inline = new_url_dict.get('inline')
post_data = new_url_dict.get('post_data')
replace = new_url_dict.get('replace')
assert url
url_info = parse_url_or_log(url)
if not url_info:
return
kwargs = dict(link_type=link_type, post_data=post_data)
if replace:
url_item.url_table.remove_one(url)
url_item.add_child_url(url_info.url, inline=inline, **kwargs)
def _process_url_item(self, url_record):
'''Process an item.
Args:
url_item (:class:`.database.URLRecord`): The item to process.
This function calls :meth:`.processor.BaseProcessor.process`.
Coroutine.
'''
assert url_record
url_info = parse_url_or_log(url_record.url)
if not url_info:
url_item = URLItem(self._url_table, None, url_record)
url_item.skip()
return
url_item = URLItem(self._url_table, url_info, url_record)
_logger.debug(
__('Begin session for {0} {1}.', url_record, url_item.url_info))
yield From(self._processor.process(url_item))
assert url_item.is_processed
self._statistics.mark_done(url_info)
if self._statistics.is_quota_exceeded:
_logger.debug('Stopping due to quota.')
self.stop()
_logger.debug(
__('End session for {0} {1}.', url_item.url_record,
url_item.url_info))
def _process_url_item(self, url_record):
'''Process an item.
Args:
url_item (:class:`.database.URLRecord`): The item to process.
This function calls :meth:`.processor.BaseProcessor.process`.
Coroutine.
'''
assert url_record
url_info = parse_url_or_log(url_record.url)
if not url_info:
url_item = URLItem(self._url_table, None, url_record)
url_item.skip()
return
url_item = URLItem(self._url_table, url_info, url_record)
_logger.debug(__('Begin session for {0} {1}.',
url_record, url_item.url_info))
yield From(self._processor.process(url_item))
assert url_item.is_processed
self._statistics.mark_done(url_info)
if self._statistics.is_quota_exceeded:
_logger.debug('Stopping due to quota.')
self.stop()
_logger.debug(__('End session for {0} {1}.',
url_item.url_record, url_item.url_info))
def test_parse_url_or_log(self):
self.assertTrue(parse_url_or_log('http://example.com'))
self.assertFalse(parse_url_or_log('http://'))
def test_parse_url_or_log(self):
self.assertTrue(parse_url_or_log('http://example.com'))
self.assertFalse(parse_url_or_log('http://'))
