qq_40256654的博客

import re import requests import time from bs4 import BeautifulSoup url = ‘http://www.cntour.cn/’ r = requests.get(url) print(r.encoding,len(r.text)) soup = BeautifulSoup(r.text, ‘lxml’) data = soup.s...

import urllib.parse import requests #第三方请求库 import json import jsonpath #处理json文件的的提取库 from bs4 import BeautifulSoup import os import urllib import re label = 'AI' label = urllib.parse.quo...

import requests, os, bs4 url = ‘https://xkcd.com’ os.makedirs(‘xkcd’,exist_ok = True) while not url.endswith(’#’): # download the page print('downloading the %s...'%(url)) # '%s...'%(url)对字符串及进行替换 re...