python爬虫（十七） 电影天堂爬虫1

# 电影天堂爬虫
from lxml import etree

import  requests
# 一个网址头
BASE_DOMAIN="https://www.dytt8.net"   
url="https://www.dytt8.net/html/gndy/dyzz/list_23_1.html"
headers={
    ‘User-Agent‘:"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"
}
response=requests.get(url,headers=headers)

text=response.text

html=etree.HTML(text) detail_urls=html.xpath("//table[@class=‘tbspan‘]//a/@href") for detail_url in detail_urls: print(BASE_DOMAIN+detail_url)