def _download(self, request_dict={}):
"""Methods for downloading the latest version of Site
"""
if self.method == 'POST':
truncated_params = {}
for k, v in self.parameters.iteritems():
truncated_params[k] = trunc(v, 50, ellipsis='...[truncated]')
logger.info("Now downloading case page at: %s (params: %s)" %
(self.url, truncated_params))
else:
logger.info("Now downloading case page at: %s" % self.url)
# Set up verify here and remove it from request_dict so you don't send
# it to s.get or s.post in two kwargs.
if request_dict.get('verify') is not None:
verify = request_dict['verify']
del request_dict['verify']
else:
verify = certifi.where()
# Get the response. Disallow redirects so they throw an error
s = requests.session()
s.mount('https://', self._get_adapter_instance())
if self.method == 'GET':
r = s.get(self.url,
headers={'User-Agent': 'Juriscraper'},
verify=verify,
**request_dict)
elif self.method == 'POST':
r = s.post(self.url,
headers={'User-Agent': 'Juriscraper'},
verify=verify,
data=self.parameters,
**request_dict)
elif self.method == 'LOCAL':
mr = MockRequest(url=self.url)
r = mr.get()
# Provides a hook for inheriting objects to tweak the request object.
self.tweak_request_object(r)
# Throw an error if a bad status code is returned.
r.raise_for_status()
# Tweak or set the encoding if needed
r = self._set_encoding(r)
# Provide the response in the Site object
self.r = r
self.status = r.status_code
# Grab the content
if 'json' in r.headers.get('content-type', ''):
return r.json()
else:
text = self._clean_text(r.text)
html_tree = self._make_html_tree(text)
html_tree.rewrite_links(self._link_repl)
return html_tree
def get_binary_content(download_url, cookies, adapter, method='GET'):
""" Downloads the file, covering a few special cases such as invalid SSL
certificates and empty file errors.
:param download_url: The URL for the item you wish to download.
:param cookies: Cookies that might be necessary to download the item.
:param adapter: An HTTPAdapter for use when getting content.
:param method: The HTTP method used to get the item, or "LOCAL" to get an
item during testing
:return: Two values. The first is a msg indicating any errors encountered.
If blank, that indicates success. The second value is the response object
containing the downloaded file.
"""
if not download_url:
# Occurs when a DeferredList fetcher fails.
msg = 'NoDownloadUrlError: %s\n%s' % (download_url,
traceback.format_exc())
return msg, None
# noinspection PyBroadException
try:
if method == 'LOCAL':
url = os.path.join(
settings.MEDIA_ROOT,
download_url)
mr = MockRequest(url=url)
r = mr.get()
else:
# Note that we do a GET even if site.method is POST. This is
# deliberate.
s = requests.session()
s.mount('https://', adapter)
headers = {'User-Agent': 'CourtListener'}
r = s.get(
download_url,
verify=False, # WA has a certificate we don't understand
headers=headers,
cookies=cookies
)
# test for empty files (thank you CA1)
if len(r.content) == 0:
msg = 'EmptyFileError: %s\n%s' % (download_url,
traceback.format_exc())
return msg, None
# test for and follow meta redirects
r = follow_redirections(r, s)
r.raise_for_status()
except:
msg = 'DownloadingError: %s\n%s' % (download_url,
traceback.format_exc())
return msg, None
# Success!
return '', r
def _download(self, request_dict={}):
"""Methods for downloading the latest version of Site
"""
if self.method == 'POST':
truncated_params = {}
for k, v in self.parameters.iteritems():
truncated_params[k] = trunc(v, 50, elipsize=True, elipsis='...[truncated]')
logger.info("Now downloading case page at: %s (params: %s)" % (self.url, truncated_params))
else:
logger.info("Now downloading case page at: %s" % self.url)
# Get the response. Disallow redirects so they throw an error
s = requests.session()
if self.method == 'GET':
r = s.get(self.url,
headers={'User-Agent': 'Juriscraper'},
**request_dict)
elif self.method == 'POST':
r = s.post(self.url,
headers={'User-Agent': 'Juriscraper'},
data=self.parameters,
**request_dict)
elif self.method == 'LOCAL':
mr = MockRequest(url=self.url)
r = mr.get()
# Provides a hook for inheriting objects to tweak the request object.
self.tweak_request_object(r)
# Throw an error if a bad status code is returned.
r.raise_for_status()
# If the encoding is iso-8859-1, switch it to cp1252 (a superset)
if r.encoding == 'ISO-8859-1':
r.encoding = 'cp1252'
# Provide the response in the Site object
self.r = r
self.status = r.status_code
if r.encoding is None:
# Requests detects the encoding when the item is GET'ed using
# HTTP headers, and then when r.text is accessed, if the encoding
# hasn't been set by that point. By setting the encoding here, we
# ensure that it's done by cchardet, if it hasn't been done with
# HTTP headers. This way it is done before r.text is accessed
# (which would do it with vanilla chardet). This is a big
# performance boon, and can be removed once requests is upgraded
# (https://github.com/kennethreitz/requests/pull/814/)
r.encoding = chardet.detect(r.content)['encoding']
# Grab the content
text = self._clean_text(r.text)
html_tree = html.fromstring(text)
html_tree.rewrite_links(self._link_repl)
return html_tree
def _download(self, request_dict={}):
"""Methods for downloading the latest version of Site
"""
if self.method == 'POST':
truncated_params = {}
for k, v in self.parameters.iteritems():
truncated_params[k] = trunc(v, 50, elipsize=True, elipsis='...[truncated]')
logger.info("Now downloading case page at: %s (params: %s)" % (self.url, truncated_params))
else:
logger.info("Now downloading case page at: %s" % self.url)
# Get the response. Disallow redirects so they throw an error
s = requests.session()
if self.method == 'GET':
r = s.get(self.url,
headers={'User-Agent': 'Juriscraper'},
**request_dict)
elif self.method == 'POST':
r = s.post(self.url,
headers={'User-Agent': 'Juriscraper'},
data=self.parameters,
**request_dict)
elif self.method == 'LOCAL':
mr = MockRequest(url=self.url)
r = mr.get()
# Provides a hook for inheriting objects to tweak the request object.
self.tweak_request_object(r)
# Throw an error if a bad status code is returned.
r.raise_for_status()
# If the encoding is iso-8859-1, switch it to cp1252 (a superset)
if r.encoding == 'ISO-8859-1':
r.encoding = 'cp1252'
# Provide the response in the Site object
self.r = r
self.status = r.status_code
if r.encoding is None:
# Requests detects the encoding when the item is GET'ed using
# HTTP headers, and then when r.text is accessed, if the encoding
# hasn't been set by that point. By setting the encoding here, we
# ensure that it's done by cchardet, if it hasn't been done with
# HTTP headers. This way it is done before r.text is accessed
# (which would do it with vanilla chardet). This is a big
# performance boon, and can be removed once requests is upgraded
# (https://github.com/kennethreitz/requests/pull/814/)
r.encoding = chardet.detect(r.content)['encoding']
# Grab the content
text = self._clean_text(r.text)
html_tree = html.fromstring(text)
html_tree.rewrite_links(self._link_repl)
return html_tree
def get_binary_content(download_url, cookies, method='GET'):
""" Downloads the file, covering a few special cases such as invalid SSL certificates and empty file errors.
:param download_url: The URL for the item you wish to download.
:param cookies: Cookies that might be necessary to download the item.
:param method: The HTTP method used to get the item, or "LOCAL" to get an item during testing
:return: Two values. The first is a msg indicating any errors encountered. If blank, that indicates success. The
second value is the response object containing the downloaded file.
"""
if not download_url:
# Occurs when a DeferredList fetcher fails.
msg = 'NoDownloadUrlError: %s\n%s' % (download_url,
traceback.format_exc())
return msg, None
# noinspection PyBroadException
try:
if method == 'LOCAL':
mr = MockRequest(
url=os.path.join(settings.INSTALL_ROOT, 'alert', download_url))
r = mr.get()
else:
# Note that we do a GET even if site.method is POST. This is deliberate.
s = requests.session()
headers = {'User-Agent': 'CourtListener'}
cookies = normalize_cookies(cookies)
logger.info("Using cookies: %s" % cookies)
try:
r = s.get(download_url, headers=headers, cookies=cookies)
except SSLError:
# Washington has a certificate we don't understand.
r = s.get(download_url,
verify=False,
headers=headers,
cookies=cookies)
# test for empty files (thank you CA1)
if len(r.content) == 0:
msg = 'EmptyFileError: %s\n%s' % (download_url,
traceback.format_exc())
return msg, r
# test for and follow meta redirects
r = follow_redirections(r, s)
except:
msg = 'DownloadingError: %s\n%s' % (download_url,
traceback.format_exc())
print msg
return msg, r
# Success!
return '', r
def get_binary_content(download_url, cookies, method='GET'):
""" Downloads the file, covering a few special cases such as invalid SSL certificates and empty file errors.
:param download_url: The URL for the item you wish to download.
:param cookies: Cookies that might be necessary to download the item.
:param method: The HTTP method used to get the item, or "LOCAL" to get an item during testing
:return: Two values. The first is a msg indicating any errors encountered. If blank, that indicates success. The
second value is the response object containing the downloaded file.
"""
if not download_url:
# Occurs when a DeferredList fetcher fails.
msg = 'NoDownloadUrlError: %s\n%s' % (download_url, traceback.format_exc())
return msg, None
# noinspection PyBroadException
try:
if method == 'LOCAL':
mr = MockRequest(url=os.path.join(settings.INSTALL_ROOT, 'alert', download_url))
r = mr.get()
else:
# Note that we do a GET even if site.method is POST. This is deliberate.
s = requests.session()
headers = {'User-Agent': 'CourtListener'}
cookies = normalize_cookies(cookies)
logger.info("Using cookies: %s" % cookies)
try:
r = s.get(download_url,
headers=headers,
cookies=cookies)
except SSLError:
# Washington has a certificate we don't understand.
r = s.get(download_url,
verify=False,
headers=headers,
cookies=cookies)
# test for empty files (thank you CA1)
if len(r.content) == 0:
msg = 'EmptyFileError: %s\n%s' % (download_url, traceback.format_exc())
return msg, r
# test for and follow meta redirects
r = follow_redirections(r, s)
except:
msg = 'DownloadingError: %s\n%s' % (download_url, traceback.format_exc())
print msg
return msg, r
# Success!
return '', r
def _download(self, request_dict={}):
"""Methods for downloading the latest version of Site
"""
if self.method == 'POST':
truncated_params = {}
for k, v in self.parameters.iteritems():
truncated_params[k] = trunc(v,
50,
elipsize=True,
elipsis='...[truncated]')
logger.info("Now downloading case page at: %s (params: %s)" %
(self.url, truncated_params))
else:
logger.info("Now downloading case page at: %s" % self.url)
# Get the response. Disallow redirects so they throw an error
s = requests.session()
if self.method == 'GET':
r = s.get(self.url,
headers={'User-Agent': 'Juriscraper'},
**request_dict)
elif self.method == 'POST':
r = s.post(self.url,
headers={'User-Agent': 'Juriscraper'},
data=self.parameters,
**request_dict)
elif self.method == 'LOCAL':
mr = MockRequest(url=self.url)
r = mr.get()
# Provides a hook for inheriting objects to tweak the request object.
self.tweak_request_object(r)
# Throw an error if a bad status code is returned.
r.raise_for_status()
# If the encoding is iso-8859-1, switch it to cp1252 (a superset)
if r.encoding == 'ISO-8859-1':
r.encoding = 'cp1252'
# Provide the response in the Site object
self.r = r
self.status = r.status_code
# Grab the content
text = self._clean_text(r.text)
html_tree = html.fromstring(text)
html_tree.rewrite_links(self._link_repl)
return html_tree
def _download(self, request_dict={}):
"""Methods for downloading the latest version of Site
"""
if self.method == 'POST':
truncated_params = {}
for k, v in self.parameters.iteritems():
truncated_params[k] = trunc(v, 50, elipsize=True, elipsis='...[truncated]')
logger.info("Now downloading case page at: %s (params: %s)" % (self.url, truncated_params))
else:
logger.info("Now downloading case page at: %s" % self.url)
# Get the response. Disallow redirects so they throw an error
s = requests.session()
if self.method == 'GET':
r = s.get(self.url,
headers={'User-Agent': 'Juriscraper'},
**request_dict)
elif self.method == 'POST':
r = s.post(self.url,
headers={'User-Agent': 'Juriscraper'},
data=self.parameters,
**request_dict)
elif self.method == 'LOCAL':
mr = MockRequest(url=self.url)
r = mr.get()
# Provides a hook for inheriting objects to tweak the request object.
self.tweak_request_object(r)
# Throw an error if a bad status code is returned.
r.raise_for_status()
# If the encoding is iso-8859-1, switch it to cp1252 (a superset)
if r.encoding == 'ISO-8859-1':
r.encoding = 'cp1252'
# Provide the response in the Site object
self.r = r
self.status = r.status_code
# Grab the content
text = self._clean_text(r.text)
html_tree = html.fromstring(text)
html_tree.rewrite_links(self._link_repl)
return html_tree
def _download(self, request_dict={}):
"""Methods for downloading the latest version of Site
"""
if self.method == 'POST':
truncated_params = {}
for k, v in self.parameters.iteritems():
truncated_params[k] = trunc(v, 50, ellipsis='...[truncated]')
logger.info("Now downloading case page at: %s (params: %s)" % (self.url, truncated_params))
else:
logger.info("Now downloading case page at: %s" % self.url)
# Set up verify here and remove it from request_dict so you don't send
# it to s.get or s.post in two kwargs.
if request_dict.get('verify') is not None:
verify = request_dict['verify']
del request_dict['verify']
else:
verify = certifi.where()
# Get the response. Disallow redirects so they throw an error
s = requests.session()
s.mount('https://', self._get_adapter_instance())
if self.method == 'GET':
r = s.get(
self.url,
headers={'User-Agent': 'Juriscraper'},
verify=verify,
**request_dict
)
elif self.method == 'POST':
r = s.post(
self.url,
headers={'User-Agent': 'Juriscraper'},
verify=verify,
data=self.parameters,
**request_dict
)
elif self.method == 'LOCAL':
mr = MockRequest(url=self.url)
r = mr.get()
# Provides a hook for inheriting objects to tweak the request object.
self.tweak_request_object(r)
# Throw an error if a bad status code is returned.
r.raise_for_status()
# Tweak or set the encoding if needed
r = self._set_encoding(r)
# Provide the response in the Site object
self.r = r
self.status = r.status_code
# Grab the content
if 'json' in r.headers.get('content-type', ''):
return r.json()
else:
text = self._clean_text(r.text)
html_tree = self._make_html_tree(text)
html_tree.rewrite_links(self._link_repl)
return html_tree
