Python爬取猫眼榜单

import urllib.request
import urllib.parse

url = "http://maoyan.com/board/4?"
headers ={“User-Agent”:“Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36”}

i = 1
while 1:
offset = (i-1)*10
parms = {‘offset’:offset}
parms = urllib.parse.urlencode(parms)
urls = url + parms
request = urllib.request.Request(urls,headers =headers)
response = urllib.request.urlopen(request)
html = response.read().decode(“utf-8”)

with open("第%d页.html" % i, 'a', encoding='utf-8') as f:
    print("正在写入第%d页" % i)
    f.write(html)
    print("第%d页写入完成" % i)

# if  not response:
#     print("爬取已完成，爬虫自动关闭")
#     break
num = input("是否继续爬取（y/n）")

if num == "y":
    i = i + 1
    offset = (i - 1) * 10
    if offset > 90:
        print("已全部爬取，爬虫自动关闭")
        break
    parms = {'offset': offset}
    parms = urllib.parse.urlencode(parms)
    urls = url + parms
    request = urllib.request.Request(urls, headers=headers)
    response = urllib.request.urlopen(request)
    html = response.read().decode("utf-8")



else:
    print("爬取结束谢谢使用")
    break

with open(“第%d页.html”%i,‘w’,encoding=‘utf-8’) as f:

print(“正在写入第%d页”%i)

f.write(html)

print(“第%d页写入完成”%i)