python学习，新浪新闻的爬取和CSDN博文爬取

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/VABTC/article/details/84784033

import urllib.request
import ssl
import re#导入正则表达式模块
data=urllib.request.urlopen("http://news.sina.com.cn/").read()#将网址信息读取出来，并赋值给data
#headers=("","")#此处可以添加模拟http请求,详见前面博文
#opener...
#opener
data2=data.decode("utf-8","ignore")#编码
pat='href="(http://news.sina.com.cn/.*?)"'
allurl=re.compile(pat).findall(data2)
for i in range(0,len(allurl)):
    try:
        print("第"+str(i)+"次爬取")
        thisurl=allurl[i]
        file="E:/practice/sinanews/"+str(i)+".html"
        urllib.request.urlretrieve(thisurl,file)#下载网页
        print("---成功---")
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e,"reason"):
            print(e.reason)

import urllib.request
import  re
url="http://blog.csdn.net/"
headers=("User-Agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.53 Safari/537.36")
opener=urllib.request.build_opener()
opener.addheaders=[headers]
urllib.request.install_opener(opener)
data=urllib.request.urlopen(url).read().decode("utf-8","ignore")
pat='href="(https://blog.csdn.net/.*?)"'
result=re.compile(pat).findall(data)
for i in range(0,len(result)):
    try:
        print("第"+str(i)+"次爬取")
        thisurl=result[i]
        file="E:/practice/csdntitle/"+str(i)+".html"
        urllib.request.urlretrieve(thisurl,file)
        print("成功")
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e,"reason"):
            print(e.reason)