爬取网站url

This commit is contained in:
zeek 2020-03-21 22:09:14 +08:00
父節點 e1ab9b83b7
當前提交 28690a838b
共有 2 個文件被更改,包括 45 次插入0 次删除

44
get_url.py Executable file
查看文件

@ -0,0 +1,44 @@
#!/usr/bin/env python
# coding=utf-8
# -*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup
urlmine = "https://git.zeekling.cn/"
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'
}
def getlinks(url):
pages = requests.get(url)
html = pages.text
soup = BeautifulSoup(html, 'html.parser')
links = soup.find_all('a')
return filterlinks(links, url)
def filterlinks(links, url_org):
tmplinks = []
for link in links:
url = str(link['href'])
ishttp = url.startswith('http')
ismine = url.startswith(urlmine)
if ishttp and (not ismine):
continue
if url.startswith('#') or '/' == url.strip():
continue
if url.startswith("?"):
continue
if not ishttp:
url = url_org + url
tmplinks.append(url)
reslinks = list(set(tmplinks))
return reslinks
links = getlinks(urlmine)
for link in links:
print(link)

1
requirement.txt Normal file
查看文件

@ -0,0 +1 @@
BeautifulSoup4