fix code Complexity (#8)
* fix code Complexity * Update wrapper.py * codefactor badge
This commit is contained in:
parent
0ca6710334
commit
444675538f
@ -5,6 +5,7 @@
|
|||||||
[![Codacy Badge](https://api.codacy.com/project/badge/Grade/255459cede9341e39436ec8866d3fb65)](https://www.codacy.com/manual/akamhy/waybackpy?utm_source=github.com&utm_medium=referral&utm_content=akamhy/waybackpy&utm_campaign=Badge_Grade)
|
[![Codacy Badge](https://api.codacy.com/project/badge/Grade/255459cede9341e39436ec8866d3fb65)](https://www.codacy.com/manual/akamhy/waybackpy?utm_source=github.com&utm_medium=referral&utm_content=akamhy/waybackpy&utm_campaign=Badge_Grade)
|
||||||
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/akamhy/waybackpy/blob/master/LICENSE)
|
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/akamhy/waybackpy/blob/master/LICENSE)
|
||||||
[![Maintainability](https://api.codeclimate.com/v1/badges/942f13d8177a56c1c906/maintainability)](https://codeclimate.com/github/akamhy/waybackpy/maintainability)
|
[![Maintainability](https://api.codeclimate.com/v1/badges/942f13d8177a56c1c906/maintainability)](https://codeclimate.com/github/akamhy/waybackpy/maintainability)
|
||||||
|
[![CodeFactor](https://www.codefactor.io/repository/github/akamhy/waybackpy/badge)](https://www.codefactor.io/repository/github/akamhy/waybackpy)
|
||||||
[![made-with-python](https://img.shields.io/badge/Made%20with-Python-1f425f.svg)](https://www.python.org/)
|
[![made-with-python](https://img.shields.io/badge/Made%20with-Python-1f425f.svg)](https://www.python.org/)
|
||||||
![pypi](https://img.shields.io/pypi/v/wayback.svg)
|
![pypi](https://img.shields.io/pypi/v/wayback.svg)
|
||||||
![PyPI - Python Version](https://img.shields.io/pypi/pyversions/waybackpy?style=flat-square)
|
![PyPI - Python Version](https://img.shields.io/pypi/pyversions/waybackpy?style=flat-square)
|
||||||
|
@ -31,25 +31,29 @@ def wayback_timestamp(**kwargs):
|
|||||||
str(kwargs["minute"]).zfill(2)
|
str(kwargs["minute"]).zfill(2)
|
||||||
)
|
)
|
||||||
|
|
||||||
|
def handle_HTTPError(e):
|
||||||
|
if e.code == 502:
|
||||||
|
raise BadGateWay(e)
|
||||||
|
elif e.code == 503:
|
||||||
|
raise WaybackUnavailable(e)
|
||||||
|
elif e.code == 429:
|
||||||
|
raise TooManyArchivingRequests(e)
|
||||||
|
elif e.code == 404:
|
||||||
|
raise UrlNotFound(e)
|
||||||
|
|
||||||
def save(url, UA=default_UA):
|
def save(url, UA=default_UA):
|
||||||
base_save_url = "https://web.archive.org/save/"
|
url_check(url)
|
||||||
request_url = (base_save_url + clean_url(url))
|
request_url = ("https://web.archive.org/save/" + clean_url(url))
|
||||||
|
|
||||||
hdr = { 'User-Agent' : '%s' % UA } #nosec
|
hdr = { 'User-Agent' : '%s' % UA } #nosec
|
||||||
req = Request(request_url, headers=hdr) #nosec
|
req = Request(request_url, headers=hdr) #nosec
|
||||||
url_check(url)
|
|
||||||
|
|
||||||
try:
|
try:
|
||||||
response = urlopen(req) #nosec
|
response = urlopen(req) #nosec
|
||||||
except HTTPError as e:
|
except HTTPError as e:
|
||||||
if e.code == 502:
|
if handle_HTTPError(e) is None:
|
||||||
raise BadGateWay(e)
|
raise PageNotSaved(e)
|
||||||
elif e.code == 503:
|
|
||||||
raise WaybackUnavailable(e)
|
|
||||||
elif e.code == 429:
|
|
||||||
raise TooManyArchivingRequests(e)
|
|
||||||
elif e.code == 404:
|
|
||||||
raise UrlNotFound(e)
|
|
||||||
else:
|
|
||||||
raise PageNotSaved(e)
|
|
||||||
except URLError:
|
except URLError:
|
||||||
try:
|
try:
|
||||||
response = urlopen(req) #nosec
|
response = urlopen(req) #nosec
|
||||||
@ -57,16 +61,17 @@ def save(url, UA=default_UA):
|
|||||||
raise UrlNotFound(e)
|
raise UrlNotFound(e)
|
||||||
|
|
||||||
header = response.headers
|
header = response.headers
|
||||||
|
|
||||||
if "exclusion.robots.policy" in str(header):
|
if "exclusion.robots.policy" in str(header):
|
||||||
raise ArchivingNotAllowed("Can not archive %s. Disabled by site owner." % (url))
|
raise ArchivingNotAllowed("Can not archive %s. Disabled by site owner." % (url))
|
||||||
archive_id = header['Content-Location']
|
|
||||||
archived_url = "https://web.archive.org" + archive_id
|
return "https://web.archive.org" + header['Content-Location']
|
||||||
return archived_url
|
|
||||||
|
|
||||||
def get(url, encoding=None, UA=default_UA):
|
def get(url, encoding=None, UA=default_UA):
|
||||||
url_check(url)
|
url_check(url)
|
||||||
hdr = { 'User-Agent' : '%s' % UA }
|
hdr = { 'User-Agent' : '%s' % UA }
|
||||||
req = Request(clean_url(url), headers=hdr) #nosec
|
req = Request(clean_url(url), headers=hdr) #nosec
|
||||||
|
|
||||||
try:
|
try:
|
||||||
resp=urlopen(req) #nosec
|
resp=urlopen(req) #nosec
|
||||||
except URLError:
|
except URLError:
|
||||||
@ -74,13 +79,14 @@ def get(url, encoding=None, UA=default_UA):
|
|||||||
resp=urlopen(req) #nosec
|
resp=urlopen(req) #nosec
|
||||||
except URLError as e:
|
except URLError as e:
|
||||||
raise UrlNotFound(e)
|
raise UrlNotFound(e)
|
||||||
|
|
||||||
if encoding is None:
|
if encoding is None:
|
||||||
try:
|
try:
|
||||||
encoding= resp.headers['content-type'].split('charset=')[-1]
|
encoding= resp.headers['content-type'].split('charset=')[-1]
|
||||||
except AttributeError:
|
except AttributeError:
|
||||||
encoding = "UTF-8"
|
encoding = "UTF-8"
|
||||||
encoding = encoding.replace("text/html","UTF-8",1)
|
|
||||||
return resp.read().decode(encoding)
|
return resp.read().decode(encoding.replace("text/html", "UTF-8", 1))
|
||||||
|
|
||||||
def near(
|
def near(
|
||||||
url,
|
url,
|
||||||
@ -96,15 +102,12 @@ def near(
|
|||||||
request_url = "https://archive.org/wayback/available?url=%s×tamp=%s" % (clean_url(url), str(timestamp))
|
request_url = "https://archive.org/wayback/available?url=%s×tamp=%s" % (clean_url(url), str(timestamp))
|
||||||
hdr = { 'User-Agent' : '%s' % UA }
|
hdr = { 'User-Agent' : '%s' % UA }
|
||||||
req = Request(request_url, headers=hdr) # nosec
|
req = Request(request_url, headers=hdr) # nosec
|
||||||
|
|
||||||
try:
|
try:
|
||||||
response = urlopen(req) #nosec
|
response = urlopen(req) #nosec
|
||||||
except HTTPError as e:
|
except HTTPError as e:
|
||||||
if e.code == 502:
|
handle_HTTPError(e)
|
||||||
raise BadGateWay(e)
|
|
||||||
elif e.code == 503:
|
|
||||||
raise WaybackUnavailable(e)
|
|
||||||
elif e.code == 404:
|
|
||||||
raise UrlNotFound(e)
|
|
||||||
data = json.loads(response.read().decode("UTF-8"))
|
data = json.loads(response.read().decode("UTF-8"))
|
||||||
if not data["archived_snapshots"]:
|
if not data["archived_snapshots"]:
|
||||||
raise ArchiveNotFound("'%s' is not yet archived." % url)
|
raise ArchiveNotFound("'%s' is not yet archived." % url)
|
||||||
|
Loading…
Reference in New Issue
Block a user