小小的爬取了猫眼

这里我只小小的爬取了 一页

import requests
import re
import time
from lxml import html
import csv
#1.进入总的电影页面
def url_data(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36',
    'Cookie':''}
    resp = requests.get(url, headers=headers)
    return resp.text
#2.在总的电影页面得到具体的url
def data(txt):
    pat = '<p class="name"><a href="(.*?)"'
    url = re.compile(pat).findall(txt)
    urls=[]
    for i in url:
        u='https://maoyan.com'+i
        urls.append(u)
    return urls
#3.进入详细页面得到数据    这里因为时间和上映地方是一起的  爬取后  可以在excel表格中分开
def xinxi(url):
    headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36',
             'Cookie':''}
    txt=requests.get(url,headers=headers).text
    text=html.etree.HTML(txt)
    name=text.xpath('//h1/text()')[0]
    palce=text.xpath('//li[@class="ellipsis"][3]/text()')[0]
    xinxis={"电影名":name,"上映地方":palce}           
    return xinxis
def main():
    basis_url='https://maoyan.com/board/4?offset='
    headers = ('电影名', '上映地方')
    with open('文件名字', 'a', encoding='utf-8',newline='') as fp:   #在这里建立文件 可以避免在下面建立文件重复打开文件
        writer = csv.DictWriter(fp, headers)
        writer.writeheader()
        for i in range(0,10,10):       #发现url规律是 以 10 递增
            url=basis_url+str(i)
            txt=url_data(url)
            urls=data(txt)
            time.sleep(5)
            for j in urls:
                information=xinxi(j)
                time.sleep(10)
                # 写入csv文件
                writer.writerow(information)
                print('已成功一部')
if __name__ == '__main__':
    main()