python爬虫之美剧排行榜爬取(加浏览器伪装，代理，异常处理)

爬取网址：http://www.meijutt.com/alltop_hit.html
爬取内容：排行榜名称
爬取目标：存储到本地文件中

涉及，浏览器伪装，代理服务器，异常处理

代码如下：

from bs4 import BeautifulSoup    #调用库
from urllib import request,error
try:
    url = 'http://www.meijutt.com/alltop_hit.html'
    headers = ("User-Agent",
               "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.79 Safari/537.36 Edge/14.14393")

    proxy_ip = '119.28.194.66'  #代理服务器ip
    proxy_ip_address = request.ProxyHandler({"http:": proxy_ip})
    openner = request.build_opener(proxy_ip_address, request.HTTPHandler)  #使用代理ip
    openner.addheaders = [headers]   #浏览器伪装
    request.install_opener(openner)
    data = openner.open(url).read().decode("gb2312")  #获取网页源码并解码

    file = open(r"E:\crawl\meiju.txt", "a")
    i = 1
    soup = BeautifulSoup(data,"html.parser")
    nodes = soup.find_all("a",target="_blank")
    for node in nodes:
        file.write(str(i)+".")
        file.write(node.text.replace("\n","")+"\n")     #将文件写入指定的文件中
        i+=1
except error.URLError as e:
    print("再检查下程序吧！")