Created
August 15, 2018 11:06
-
-
Save drewbitt/43cab7b6c0792b30a46d65c226a741db to your computer and use it in GitHub Desktop.
Get all links on madokami page & append to list file, --group to specify text criteria in link title
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/python3 | |
import httplib2 | |
import base64 | |
import re | |
import argparse | |
from bs4 import BeautifulSoup | |
parser = argparse.ArgumentParser() | |
parser.add_argument("madokami_url",nargs=1) | |
parser.add_argument("-group", "--group") | |
args = parser.parse_args() | |
username = "" | |
password = "" | |
h = httplib2.Http() | |
data_str = str(username) + ':' + str(password) | |
auth = base64.encodestring(data_str.encode("utf-8")) | |
status, response = h.request( | |
args.madokami_url[0], | |
'GET', | |
headers = { 'Authorization' : 'Basic ' + auth.decode("utf-8") }) | |
soup = BeautifulSoup(response, 'lxml') | |
f = open("list", "a+") | |
webfull = 'https://manga.madokami.al' | |
if args.group: | |
regexp = re.compile(args.group) | |
for tag in soup.find_all(rel="nofollow"): | |
if regexp.search(tag.contents[0]): | |
f.write(webfull + tag.get('href') + '\n') | |
else: | |
for link in soup.find_all(rel="nofollow"): | |
f.write(webfull + link.get('href') + '\n') | |
f.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment