def prepare_url(url, params):
"""Prepares the given HTTP URL."""
#: Accept objects that have string representations.
#: We're unable to blindly call unicode/str functions
#: as this will include the bytestring indicator (b'')
#: on python 3.x.
#: https://github.com/kennethreitz/requests/pull/2238
if isinstance(url, bytes):
url = url.decode('utf8')
else:
url = unicode(url) if is_py2 else str(url)
# Don't do any URL preparation for non-HTTP schemes like `mailto`,
# `data` etc to work around exceptions from `url_parse`, which
# handles RFC 3986 only.
if ':' in url and not url.lower().startswith('http'):
return url
# Support for unicode domain names and paths.
try:
scheme, auth, host, port, path, query, fragment = urllib3.util.url.parse_url(
url)
except LocationParseError as e:
raise InvalidURL(*e.args)
if not scheme:
error = (
"Invalid URL {0!r}: No schema supplied. Perhaps you meant http://{0}?"
)
error = error.format(to_native_string(url, 'utf8'))
raise MissingSchema(error)
if not host:
raise InvalidURL("Invalid URL %r: No host supplied" % url)
# Only want to apply IDNA to the hostname
try:
host = host.encode('idna').decode('utf-8')
except UnicodeError:
raise InvalidURL('URL has an invalid label.')
# Carefully reconstruct the network location
netloc = auth or ''
if netloc:
netloc += '@'
netloc += host
if port:
netloc += ':' + str(port)
# Bare domains aren't valid URLs.
if not path:
path = '/'
if is_py2:
if isinstance(scheme, str):
scheme = scheme.encode('utf-8')
if isinstance(netloc, str):
netloc = netloc.encode('utf-8')
if isinstance(path, str):
path = path.encode('utf-8')
if isinstance(query, str):
query = query.encode('utf-8')
if isinstance(fragment, str):
fragment = fragment.encode('utf-8')
if isinstance(params, (str, bytes)):
params = to_native_string(params)
enc_params = encode_params(params)
if enc_params:
if query:
query = '%s&%s' % (query, enc_params)
else:
query = enc_params
url = requote_uri(urlunparse([scheme, netloc, path, None, query,
fragment]))
return url
def prepare_url(url, params):
"""Prepares the given HTTP URL."""
#: Accept objects that have string representations.
#: We're unable to blindly call unicode/str functions
#: as this will include the bytestring indicator (b'')
#: on python 3.x.
#: https://github.com/kennethreitz/requests/pull/2238
if isinstance(url, bytes):
url = url.decode('utf8')
else:
url = unicode(url) if is_py2 else str(url)
# Don't do any URL preparation for non-HTTP schemes like `mailto`,
# `data` etc to work around exceptions from `url_parse`, which
# handles RFC 3986 only.
if ':' in url and not url.lower().startswith('http'):
return url
# Support for unicode domain names and paths.
try:
scheme, auth, host, port, path, query, fragment = urllib3.util.url.parse_url(url)
except LocationParseError as e:
raise InvalidURL(*e.args)
if not scheme:
error = ("Invalid URL {0!r}: No schema supplied. Perhaps you meant http://{0}?")
error = error.format(to_native_string(url, 'utf8'))
raise MissingSchema(error)
if not host:
raise InvalidURL("Invalid URL %r: No host supplied" % url)
# Only want to apply IDNA to the hostname
try:
host = host.encode('idna').decode('utf-8')
except UnicodeError:
raise InvalidURL('URL has an invalid label.')
# Carefully reconstruct the network location
netloc = auth or ''
if netloc:
netloc += '@'
netloc += host
if port:
netloc += ':' + str(port)
# Bare domains aren't valid URLs.
if not path:
path = '/'
if is_py2:
if isinstance(scheme, str):
scheme = scheme.encode('utf-8')
if isinstance(netloc, str):
netloc = netloc.encode('utf-8')
if isinstance(path, str):
path = path.encode('utf-8')
if isinstance(query, str):
query = query.encode('utf-8')
if isinstance(fragment, str):
fragment = fragment.encode('utf-8')
if isinstance(params, (str, bytes)):
params = to_native_string(params)
enc_params = encode_params(params)
if enc_params:
if query:
query = '%s&%s' % (query, enc_params)
else:
query = enc_params
url = requote_uri(urlunparse([scheme, netloc, path, None, query, fragment]))
return url
def _load(self, path, skipcrawl=False, originaluri=None, includelogs=False,\
skipinit=False, loadtype='href', loadcomplete=False):
"""Helper function to main load function.
:param path: path to start load from.
:type path: str.
:param skipcrawl: flag to determine if load should traverse found links.
:type skipcrawl: boolean.
:param originaluri: variable to assist in determining originating path.
:type originaluri: str.
:param includelogs: flag to determine if logs should be downloaded also.
:type includelogs: boolean.
:param skipinit: flag to determine if first run of load.
:type skipinit: boolean.
:param loadtype: flag to determine if load is meant for only href items.
:type loadtype: str.
:param loadcomplete: flag to download the entire monolith
:type loadcomplete: boolean
"""
if path.endswith("?page=1"):
return
elif not includelogs:
if "/Logs/" in path:
return
#TODO: need to find a better way to support non ascii characters
path = path.replace("|", "%7C")
#remove fragments
newpath = urlparse2.urlparse(path)
newpath.fragment = ''
path = urlparse2.urlunparse(newpath)
LOGGER.debug(u'_loading %s', path)
if not self.reload:
if path.lower() in self._visited_urls:
return
resp = self._client.get(path)
if resp.status != 200 and path.lower() == self._client.typepath.defs.\
biospath:
raise BiosUnregisteredError()
elif resp.status != 200:
path = path + '/'
resp = self._client.get(path)
if resp.status == 401:
raise SessionExpiredRis("Invalid session. Please logout and "\
"log back in or include credentials.")
elif resp.status != 200:
return
if loadtype == "ref":
self.parse_schema(resp)
self.queue.put((resp, path, skipinit, self))
if loadtype == 'href':
#follow all the href attributes
if self.is_redfish:
jsonpath_expr = jsonpath_rw.parse(u"$..'@odata.id'")
else:
jsonpath_expr = jsonpath_rw.parse(u'$..href')
matches = jsonpath_expr.find(resp.dict)
if 'links' in resp.dict and 'NextPage' in resp.dict['links']:
if originaluri:
next_link_uri = originaluri + '?page=' + \
str(resp.dict['links']['NextPage']['page'])
href = u'%s' % next_link_uri
self._load(href, originaluri=originaluri, \
includelogs=includelogs, skipcrawl=skipcrawl, \
skipinit=skipinit)
else:
next_link_uri = path + '?page=' + \
str(resp.dict['links']['NextPage']['page'])
href = u'%s' % next_link_uri
self._load(href, originaluri=path, includelogs=includelogs,\
skipcrawl=skipcrawl, skipinit=skipinit)
(newversion, dirmatch) = self.check_for_directory(matches)
if not newversion and not skipcrawl:
for match in matches:
if path == "/rest/v1":
if str(match.full_path) == "links.Schemas.href" or \
str(match.full_path) == "links.Registries.href":
continue
else:
if str(match.full_path) == "*****@*****.**" or \
str(match.full_path) == "*****@*****.**":
continue
if match.value == path:
continue
href = u'%s' % match.value
self._load(href, skipcrawl=skipcrawl, \
originaluri=originaluri, includelogs=includelogs, \
skipinit=skipinit)
elif not skipcrawl:
href = u'%s' % dirmatch.value
self._load(href, skipcrawl=skipcrawl, originaluri=originaluri, \
includelogs=includelogs, skipinit=skipinit)
if loadcomplete:
for match in matches:
self._load(match.value, skipcrawl=skipcrawl, originaluri=\
originaluri, includelogs=includelogs, skipinit=skipinit)
def _load(self, path, skipcrawl=False, originaluri=None, includelogs=False,\
skipinit=False, loadtype='href', loadcomplete=False):
"""Helper function to main load function.
:param path: path to start load from.
:type path: str.
:param skipcrawl: flag to determine if load should traverse found links.
:type skipcrawl: boolean.
:param originaluri: variable to assist in determining originating path.
:type originaluri: str.
:param includelogs: flag to determine if logs should be downloaded also.
:type includelogs: boolean.
:param skipinit: flag to determine if first run of load.
:type skipinit: boolean.
:param loadtype: flag to determine if load is meant for only href items.
:type loadtype: str.
:param loadcomplete: flag to download the entire monolith
:type loadcomplete: boolean
"""
if path.endswith("?page=1"):
return
elif not includelogs:
if "/Logs/" in path:
return
#TODO: need to find a better way to support non ascii characters
path = path.replace("|", "%7C")
#remove fragments
newpath = urlparse2.urlparse(path)
newpath.fragment = ''
path = urlparse2.urlunparse(newpath)
LOGGER.debug(u'_loading %s', path)
if not self.reload:
if path.lower() in self._visited_urls:
return
resp = self._client.get(path)
if resp.status != 200:
path = path + '/'
resp = self._client.get(path)
if resp.status == 401:
raise SessionExpiredRis("Invalid session. Please logout and "\
"log back in or include credentials.")
elif resp.status != 200:
return
self.queue.put((resp, path, skipinit, self))
if loadtype == 'href':
#follow all the href attributes
jsonpath_expr = jsonpath_rw.parse(u"$..'@odata.id'")
matches = jsonpath_expr.find(resp.dict)
if 'links' in resp.dict and 'NextPage' in resp.dict['links']:
if originaluri:
next_link_uri = originaluri + '?page=' + \
str(resp.dict['links']['NextPage']['page'])
href = u'%s' % next_link_uri
self._load(href, originaluri=originaluri, \
includelogs=includelogs, skipcrawl=skipcrawl, \
skipinit=skipinit)
else:
next_link_uri = path + '?page=' + \
str(resp.dict['links']['NextPage']['page'])
href = u'%s' % next_link_uri
self._load(href, originaluri=path, includelogs=includelogs,\
skipcrawl=skipcrawl, skipinit=skipinit)
if not skipcrawl:
for match in matches:
if str(match.full_path) == "*****@*****.**" or \
str(match.full_path) == "*****@*****.**":
continue
if match.value == path:
continue
href = u'%s' % match.value
self._load(href, skipcrawl=skipcrawl, \
originaluri=originaluri, includelogs=includelogs, \
skipinit=skipinit)
if loadcomplete:
for match in matches:
self._load(match.value, skipcrawl=skipcrawl, originaluri=\
originaluri, includelogs=includelogs, skipinit=skipinit)
def parse_list_page(self, response):
multi_xpath = '/html/body/div[@id and @class="c"]'
html5_response = response_html5parse(response)
hxs = HtmlXPathSelector(html5_response)
multi_hxs = hxs.select(multi_xpath)
list_url = response.url
query = response.meta.get('query')
for hxs in multi_hxs:
nick = ''.join(hxs.select('./div[1]/a//text()').extract())
user_url = ''.join(hxs.select('./div[1]/a/@href').extract())
user_url = urllib.unquote(user_url).strip()
user_url_up = urlparse(user_url)
user_url_up.query = ''
user_url = urlunparse(user_url_up)
div3 = hxs.select('./div[3]')
if div3:
content = ''.join(div3.select('.//text()').extract()[1:-10])
else:
content = ''.join(hxs.select('./div[1]/span//text()').extract())
misc1 = hxs.select('.//a//text()')
zan_count, zhuanfa_count, pinglun_count = self._ana_misc1(misc1)
misc2 = hxs.select('.//span[@class="ct"]//text()')
time, from_info = self._ana_misc2(misc2)
misc3 = hxs.select('.//a[@class="cc"]/@href')
own_msg_id, forward_msg_id = self._get_msg_id(misc3)
own_user_id, forward_user_id = self._get_user_id(misc3)
if forward_msg_id and forward_user_id:
is_forward = True
forward_msg_url1 = 'http://weibo.com/%s/%s' % (forward_user_id, forward_msg_id)
forward_msg_url2 = 'http://weibo.cn/%s/%s' % (forward_user_id, forward_msg_id)
else:
is_forward = False
forward_msg_url1 = ''
forward_msg_url2 = ''
doc = {
'data_source': '新浪微博搜索',
'nick': nick,
'user_url': user_url,
'content': content,
'zan_count': zan_count,
'zhuanfa_count': zhuanfa_count,
'pinglun_count': pinglun_count,
'time': time,
'from_info': from_info,
'own_user_id': own_user_id,
'own_msg_id': own_msg_id,
'own_msg_url1': 'http://weibo.com/%s/%s' % (own_user_id, own_msg_id),
'own_msg_url2': 'http://weibo.cn/%s/%s' % (own_user_id, own_msg_id),
'forward_user_id': forward_user_id,
'forward_msg_id': forward_msg_id,
'forward_msg_url1': forward_msg_url1,
'forward_msg_url2': forward_msg_url2,
'is_forward': is_forward,
'sort': self.sort,
}
#暂不处理weibo用户的首页头像
# user_homepage = user_url
# if not user_homepage:
# next_request = None
# else:
# next_request = Request(user_homepage, callback=self.parse_user_homepage)
item = WeiboItem(doc=doc,
next_request=None, list_url=list_url, query=query)
yield self.item_or_request(item)
#暂不处理weibo用户的首页头像
# def parse_user_homepage(self, response):
# item = response.meta['item']
# item['doc']['detail'] = response.body_as_unicode()
# yield self.item_or_request(item)
