Benjamin_Loison/waybackpy
1
0
Fork 0
Code Issues 1 Pull Requests Packages Projects Releases Wiki Activity

deleted .travis.yml, link with flake (#41)

Browse Source 
close #38
This commit is contained in:
Akash Mahanty 2020-11-26 13:06:50 +05:30 committed by GitHub
parent 525cf17c6f
commit ca51c14332
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 62 additions and 58 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
.travis.yml
View File

@ -1,17 +0,0 @@
language: python
os: linux
dist: xenial
cache: pip
python:
- 3.8
before_install:
- python --version
- pip install -U pip
- pip install -U pytest
- pip install codecov
- pip install pytest pytest-cov
script:
- cd tests
- pytest --cov=../waybackpy
after_success:
- python -m codecov

22
setup.py
View File

@ -9,20 +9,20 @@ with open(os.path.join(os.path.dirname(__file__), 'waybackpy', '__version__.py')
exec(f.read(), about)
setup(
name = about['__title__'],
packages = ['waybackpy'],
version = about['__version__'],
description = about['__description__'],
name=about['__title__'],
packages=['waybackpy'],
version=about['__version__'],
description=about['__description__'],
long_description=long_description,
long_description_content_type='text/markdown',
license= about['__license__'],
author = about['__author__'],
author_email = about['__author_email__'],
url = about['__url__'],
download_url = 'https://github.com/akamhy/waybackpy/archive/2.2.0.tar.gz',
keywords = ['waybackpy', 'archive', 'archive website', 'wayback machine', 'Internet Archive'],
license=about['__license__'],
author=about['__author__'],
author_email=about['__author_email__'],
url=about['__url__'],
download_url='https://github.com/akamhy/waybackpy/archive/2.2.0.tar.gz',
keywords=['waybackpy', 'archive', 'archive website', 'wayback machine', 'Internet Archive'],
install_requires=[],
python_requires= ">=3.4",
python_requires=">=3.4",
classifiers=[
'Development Status :: 5 - Production/Stable',
'Intended Audience :: Developers',

0
tests/__init__.py Normal file
View File

5
waybackpy/__version__.py
View File

@ -1,7 +1,10 @@
# -*- coding: utf-8 -*-
__title__ = "waybackpy"
__description__ = "A Python package that interfaces with the Internet Archive's Wayback Machine API. Archive pages and retrieve archived pages easily."
__description__ = (
"A Python package that interfaces with the Internet Archive's Wayback Machine API. "
"Archive pages and retrieve archived pages easily."
)
__url__ = "https://akamhy.github.io/waybackpy/"
__version__ = "2.2.0"
__author__ = "akamhy"

36
waybackpy/cli.py
View File

@ -8,24 +8,31 @@ import random
from waybackpy.wrapper import Url
from waybackpy.__version__ import __version__
def _save(obj):
return (obj.save())
def _archive_url(obj):
return (obj.archive_url)
def _json(obj):
return (obj.JSON)
def _oldest(obj):
return (obj.oldest())
def _newest(obj):
return (obj.newest())
def _total_archives(obj):
return (obj.total_archives())
def _near(obj, args):
_near_args = {}
if args.year:
@ -40,8 +47,9 @@ def _near(obj, args):
_near_args["minute"] = args.minute
return (obj.near(**_near_args))
def _save_urls_on_file(input_list, live_url_count):
m = re.search('https?://([A-Za-z_0-9.-]+).*', input_list[0]) # O(1)
m = re.search('https?://([A-Za-z_0-9.-]+).*', input_list[0])
if m:
domain = m.group(1)
else:
@ -50,12 +58,13 @@ def _save_urls_on_file(input_list, live_url_count):
uid = ''.join(random.choice(string.ascii_lowercase + string.digits) for _ in range(6))
file_name = "%s-%d-urls-%s.txt" % (domain, live_url_count, uid)
file_content = "\n".join(input_list) #join with \n
file_content = "\n".join(input_list)
file_path = os.path.join(os.getcwd(), file_name)
with open(file_name, "w+") as f:
with open(file_path, "w+") as f:
f.write(file_content)
return "%s\n\n'%s' saved in current working directory" % (file_content, file_name)
def _known_urls(obj, args):
"""Abbreviations:
sd = subdomain
@ -77,6 +86,7 @@ def _known_urls(obj, args):
return text
def _get(obj, args):
if args.get.lower() == "url":
return (obj.get())
@ -100,6 +110,7 @@ def _get(obj, args):
\n4) newest - get the source code of the newest archive for the supplied url.\
\n5) save - Create a new archive and get the source code of this new archive for the supplied url.")
def args_handler(args):
if args.version:
return ("waybackpy version %s" % __version__)
@ -130,7 +141,12 @@ def args_handler(args):
return _near(obj, args)
if args.get:
return _get(obj, args)
return ("You only specified the URL. But you also need to specify the operation.\nSee 'waybackpy --help' for help using this tool.")
message = (
"You only specified the URL. But you also need to specify the operation."
"\nSee 'waybackpy --help' for help using this tool."
)
return message
def parse_args(argv):
parser = argparse.ArgumentParser()
@ -139,7 +155,8 @@ def parse_args(argv):
requiredArgs.add_argument("--url", "-u", help="URL on which Wayback machine operations would occur")
userAgentArg = parser.add_argument_group('User Agent')
userAgentArg.add_argument("--user_agent", "-ua", help="User agent, default user_agent is \"waybackpy python package - https://github.com/akamhy/waybackpy\"")
help_text = "User agent, default user_agent is \"waybackpy python package - https://github.com/akamhy/waybackpy\""
userAgentArg.add_argument("--user_agent", "-ua", help=help_text)
saveArg = parser.add_argument_group("Create new archive/save URL")
saveArg.add_argument("--save", "-s", action='store_true', help="Save the URL on the Wayback machine")
@ -164,9 +181,10 @@ def parse_args(argv):
knownUrlArg = parser.add_argument_group("URLs known and archived to Waybcak Machine for the site.")
knownUrlArg.add_argument("--known_urls", "-ku", action='store_true', help="URLs known for the domain.")
knownUrlArg.add_argument("--subdomain", "-sub", action='store_true', help="Use with '--known_urls' to include known URLs for subdomains.")
knownUrlArg.add_argument("--alive", "-a", action='store_true', help="Only include live URLs. Will not inlclude dead links.")
help_text = "Use with '--known_urls' to include known URLs for subdomains."
knownUrlArg.add_argument("--subdomain", "-sub", action='store_true', help=help_text)
help_text = "Only include live URLs. Will not inlclude dead links."
knownUrlArg.add_argument("--alive", "-a", action='store_true', help=help_text)
nearArg = parser.add_argument_group('Archive close to time specified')
nearArg.add_argument("--near", "-N", action='store_true', help="Archive near specified time")
@ -182,6 +200,7 @@ def parse_args(argv):
return parser.parse_args(argv[1:])
def main(argv=None):
if argv is None:
argv = sys.argv
@ -189,5 +208,6 @@ def main(argv=None):
output = args_handler(args)
print(output)
if __name__ == "__main__":
sys.exit(main(sys.argv))

40
waybackpy/wrapper.py
View File

@ -60,6 +60,7 @@ def _get_response(req):
raise exc
return response
class Url:
"""waybackpy Url object"""
@ -67,9 +68,9 @@ class Url:
self.url = url
self.user_agent = user_agent
self._url_check() # checks url validity on init.
self.JSON = self._JSON() # JSON of most recent archive
self.archive_url = self._archive_url() # URL of archive
self.timestamp = self._archive_timestamp() # timestamp for last archive
self.JSON = self._JSON() # JSON of most recent archive
self.archive_url = self._archive_url() # URL of archive
self.timestamp = self._archive_timestamp() # timestamp for last archive
self._alive_url_list = []
def __repr__(self):
@ -79,11 +80,13 @@ class Url:
return "%s" % self.archive_url
def __len__(self):
td_max = timedelta(days=999999999,
hours=23,
minutes=59,
seconds=59,
microseconds=999999)
td_max = timedelta(
days=999999999,
hours=23,
minutes=59,
seconds=59,
microseconds=999999
)
if self.timestamp == datetime.max:
return td_max.days
else:
@ -208,14 +211,10 @@ class Url:
)
self.archive_url = archive_url
self.timestamp = datetime.strptime(data["archived_snapshots"]
["closest"]
["timestamp"],
'%Y%m%d%H%M%S')
self.timestamp = datetime.strptime(data["archived_snapshots"]["closest"]["timestamp"], '%Y%m%d%H%M%S')
return self
def oldest(self, year=1994):
"""Return the oldest Wayback Machine archive for this URL."""
return self.near(year=year)
@ -244,10 +243,11 @@ class Url:
try:
response_code = requests.get(url).status_code
except Exception as e:
return #we don't care if urls are not opening
except Exception:
return # we don't care if urls are not opening
if response_code >= 400: #200s are OK and 300s are usually redirects, if you don't want redirects replace 400 with 300
# 200s are OK and 300s are usually redirects, if you don't want redirects replace 400 with 300
if response_code >= 400:
return
self._alive_url_list.append(url)
@ -266,14 +266,12 @@ class Url:
if subdomain:
request_url = (
"https://web.archive.org/cdx/search/cdx?url=*.%s/*&output=json&fl=original&collapse=urlkey"
% self._clean_url()
"https://web.archive.org/cdx/search/cdx?url=*.%s/*&output=json&fl=original&collapse=urlkey" % self._clean_url()
)
else:
request_url = (
"http://web.archive.org/cdx/search/cdx?url=%s/*&output=json&fl=original&collapse=urlkey"
% self._clean_url()
"http://web.archive.org/cdx/search/cdx?url=%s/*&output=json&fl=original&collapse=urlkey" % self._clean_url()
)
hdr = {"User-Agent": "%s" % self.user_agent}
@ -283,7 +281,7 @@ class Url:
data = json.loads(response.read().decode("UTF-8"))
url_list = [y[0] for y in data if y[0] != "original"]
#Remove all deadURLs from url_list if alive=True
# Remove all deadURLs from url_list if alive=True
if alive:
with concurrent.futures.ThreadPoolExecutor() as executor:
executor.map(self.pick_live_urls, url_list)