dawen1937的博客

from urllib.request import urlopen from bs4 import BeautifulSoup html = urlopen("http://www.pythonscraping.com/pages/warandpeace.html") bsObj = BeautifulSoup(html) #根据css样式表查找 nameList = bsObj.findAll(

from urllib.request import urlopen from urllib.parse import urlparse from bs4 import BeautifulSoup import re import datetime import random pages = set() random.seed(datetime.datetime.now()) #获取页面内链

从网站下载图片，右键审查元素，找到 from urllib.request import urlopen from urllib.request import urlretrieve from bs4 import BeautifulSoup html = urlopen("http://www.pythonscraping.com") bsObj=BeautifulSoup(html) ur