涉世浅,点染亦浅;历事深,机械亦深。故君子与其练达,不若朴鲁;与其曲谨,不若疏狂。
pyhton爬取图片
代码语言:javascript复制# -*- coding:utf-8 -*-
import requests #调用第三方库
import re #正则
import urllib.request
#print(requests.get(url))
def rree(url):
wb_date = requests.get(url).text #获取当前网页的Html,返回Unicode格式
#返回的是一个包含服务器资源的Response对象。包含从服务器返回的所有的相关资源。
res = re.compile(r'src="(http. ?jpg)"') #正则表达式匹配图片
reg = re.findall(res,wb_date)
#print(wb_date)
return reg
def download(reg,path):
num=0
path = path
for i in reg: #遍历
print(i)
a = requests.get(i)
#f =open('%s.jpg'%nun,'wb')
f =open(path '%s.jpg'%num,'wb')
f.write(a.content)#requests.get(url).content 返回bytes格式
f.close()
num=num 1
print('第%s个图片下载完毕'%num)
if __name__ =="__main__":
#网站链接
url = input("Please input the correct url: ")
#储存位置
path = "F:/C-and-Python-Algorithn/python/interest/image/ "
reg = rree(url)
download(reg,path)
requests.get(url).text
代码语言:javascript复制<!DOCTYPE html>
<script src="/js/src/click.js"></script>
<script type="text/javascript" src="//libs.baidu.com/jquery/1.8.3/jquery.min.js"></script>
<html lang="en">
<head><meta name="generator" content="Hexo 3.9.0">
<meta charset="utf-8">
<title>AngelNI's Blog</title>
<meta name="viewport" content="width=device-width, initial-scale=1, maximum-scale=1">
<meta name="google-site-verification" content="JwzmnANXlpmQlhwaSORuqpEB6P3Sr-tRhw4R_XDRcEc">
<meta name="baidu-site-verification" content="ztPAF2oDcw">
<meta name="description" content="This is a simple record of learning bits and pieces, so that each step of learning into an unforgettable memory.">
<meta name="keywords" content="learning note">
<meta property="og:type" content="website">
<meta property="og:title" content="AngelNI's Blog">
<meta property="og:url" content="https://angelni.github.io/index.html">
......
re.compile(r’src=”(http. ?jpg)”‘)
代码语言:javascript复制<!--图片格式-->
<img class="thumbnail" src="https://s2.ax1x.com/2020/01/29/1QPiUf.jpg" alt="冬日" title="" style="">
拿我的博客举栗