Python pip._vendor.requests.Timeout() Examples
The following are 20
code examples of pip._vendor.requests.Timeout().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
pip._vendor.requests
, or try the search function
.
.
Example #1
| Source File: collector.py From rules_pip with MIT License | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: {}".format(exc))
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return _make_html_page(resp,
cache_link_parsing=link.cache_link_parsing)
return None
Example #2
| Source File: index.py From fxxkpython with GNU General Public License v3.0 | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP as exc:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except requests.HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return HTMLPage(resp.content, resp.url, resp.headers)
return None
Example #3
| Source File: index.py From fxxkpython with GNU General Public License v3.0 | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP as exc:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except requests.HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return HTMLPage(resp.content, resp.url, resp.headers)
return None
Example #4
| Source File: index.py From fxxkpython with GNU General Public License v3.0 | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP as exc:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except requests.HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return HTMLPage(resp.content, resp.url, resp.headers)
return None
Example #5
| Source File: index.py From fxxkpython with GNU General Public License v3.0 | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP as exc:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except requests.HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return HTMLPage(resp.content, resp.url, resp.headers)
return None
Example #6
| Source File: index.py From android_universal with MIT License | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP as exc:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except requests.HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return HTMLPage(resp.content, resp.url, resp.headers)
return None
Example #7
| Source File: index.py From V1EngineeringInc-Docs with Creative Commons Attribution Share Alike 4.0 International | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return HTMLPage(resp.content, resp.url, resp.headers)
return None
Example #8
| Source File: index.py From Carnets with BSD 3-Clause "New" or "Revised" License | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return HTMLPage(resp.content, resp.url, resp.headers)
return None
Example #9
| Source File: collector.py From CogAlg with MIT License | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return _make_html_page(resp)
return None
Example #10
| Source File: index.py From coffeegrindsize with MIT License | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return HTMLPage(resp.content, resp.url, resp.headers)
return None
Example #11
| Source File: index.py From Mastering-Elasticsearch-7.0 with MIT License | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return HTMLPage(resp.content, resp.url, resp.headers)
return None
Example #12
| Source File: index.py From Weapon-Detection-And-Classification with MIT License | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP as exc:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except requests.HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return HTMLPage(resp.content, resp.url, resp.headers)
return None
Example #13
| Source File: index.py From Hands-On-Application-Development-with-PyCharm with MIT License | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP as exc:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except requests.HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return HTMLPage(resp.content, resp.url, resp.headers)
return None
Example #14
| Source File: index.py From learn_python3_spider with MIT License | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP as exc:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except requests.HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return HTMLPage(resp.content, resp.url, resp.headers)
return None
Example #15
| Source File: index.py From scylla with Apache License 2.0 | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return HTMLPage(resp.content, resp.url, resp.headers)
return None
Example #16
| Source File: index.py From Building-Recommendation-Systems-with-Python with MIT License | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP as exc:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except requests.HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return HTMLPage(resp.content, resp.url, resp.headers)
return None
Example #17
| Source File: index.py From Building-Recommendation-Systems-with-Python with MIT License | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP as exc:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except requests.HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return HTMLPage(resp.content, resp.url, resp.headers)
return None
Example #18
| Source File: index.py From deepWordBug with Apache License 2.0 | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP as exc:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except requests.HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return HTMLPage(resp.content, resp.url, resp.headers)
return None
Example #19
| Source File: collector.py From pex with Apache License 2.0 | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return _make_html_page(resp)
return None
Example #20
| Source File: index.py From Mastering-Elasticsearch-7.0 with MIT License | 4 votes |
|
def _get_html_page(link, session=None):
# type: (Link, Optional[PipSession]) -> Optional[HTMLPage]
if session is None:
raise TypeError(
"_get_html_page() missing 1 required keyword argument: 'session'"
)
url = link.url.split('#', 1)[0]
# Check for VCS schemes that do not support lookup as web pages.
vcs_scheme = _match_vcs_scheme(url)
if vcs_scheme:
logger.debug('Cannot look at %s URL %s', vcs_scheme, link)
return None
# Tack index.html onto file:// URLs that point to directories
scheme, _, path, _, _, _ = urllib_parse.urlparse(url)
if (scheme == 'file' and os.path.isdir(urllib_request.url2pathname(path))):
# add trailing slash if not present so urljoin doesn't trim
# final segment
if not url.endswith('/'):
url += '/'
url = urllib_parse.urljoin(url, 'index.html')
logger.debug(' file: URL is directory, getting %s', url)
try:
resp = _get_html_response(url, session=session)
except _NotHTTP:
logger.debug(
'Skipping page %s because it looks like an archive, and cannot '
'be checked by HEAD.', link,
)
except _NotHTML as exc:
logger.debug(
'Skipping page %s because the %s request got Content-Type: %s',
link, exc.request_desc, exc.content_type,
)
except HTTPError as exc:
_handle_get_page_fail(link, exc)
except RetryError as exc:
_handle_get_page_fail(link, exc)
except SSLError as exc:
reason = "There was a problem confirming the ssl certificate: "
reason += str(exc)
_handle_get_page_fail(link, reason, meth=logger.info)
except requests.ConnectionError as exc:
_handle_get_page_fail(link, "connection error: %s" % exc)
except requests.Timeout:
_handle_get_page_fail(link, "timed out")
else:
return HTMLPage(resp.content, resp.url, resp.headers)
return None
