爬虫维基百科

#__author__ = 'DouYunQian'

 #coding=utf-8

 import re

 from bs4 import BeautifulSoup

 from urllib import request

 rep=request.urlopen("https://en.wikipedia.org/wiki/Main_Page").read().decode("utf-8")





 soup=BeautifulSoup(rep,"html.parser")



 for line in soup.find_all("a",href=re.compile("^/wiki/")):

     if re.search("\.(jpg|JPG)$",line["href"]):

         continue

     print(line.get_text(),"<---->","https://en.wikipedia.org"+line["href"])