抓取猫眼电影排行

最新推荐文章于 2021-10-17 16:23:23 发布

臣序源

最新推荐文章于 2021-10-17 16:23:23 发布

阅读量598

点赞数 1

分类专栏：学习笔记文章标签：爬虫初学

本文链接：https://blog.csdn.net/weixin_42112678/article/details/82936463

版权

学习笔记专栏收录该内容

1 篇文章 0 订阅

订阅专栏

import requests
import re

def access_to_web_pages(offset):
    headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 SE 2.X MetaSr 1.0'
    }

    url = 'http://maoyan.com/board/4?offset='+str(offset)
    response = requests.get(url,headers=headers)

    return response

def get_the_data(response):
    pattern = re.compile('<dd>.*?>(.*?)</i>.*?<p class="name">.*?>(.*?)</a>.*?<p class="star">(.*?)</p>.*?<p class="releasetime">(.*?)</p>.*?</dd>',re.S)
    items = re.findall(pattern,response.text)

    return items

def data_processing(items):

    item_list = []
    for item in items:
        item = list(item)
        item_list.append(item)

    for i in range(len(item_list)):
        item_list[i][2] = item_list[i][2].strip()

    return item_list

def save_the_data(item_list):
    
    with open('maoyan.txt','a',encoding='utf-8')as f:
        for i in item_list:
            for j in i:
                f.write(j)
                f.write('\n')

def main():
    i = 0
    while i < 10:
        offset = i * 10
        response = access_to_web_pages(offset)
        items = get_the_data(response)
        item_list = data_processing(items)
        save_the_data(item_list)
        i = i + 1

if __name__ == '__main__':
    main()