貓眼top100部高分電影spider

第一次嘗試Spider,是個突破

#encoding=utf-8

import requests
import re

class MaoYantop:
    def __init__(self):
        self.url = "https://maoyan.com/board/4?offset={}"
        self.headers = {"user-agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.70 Safari/537.36"}
        self.rank = 0

    def get_url_list(self):
        return [self.url.format(i*10) for i in range(10)]

    def parse_url(self, url):
        response = requests.get(url, headers=self.headers)
        return response.content.decode()

    def run(self):
        #1.生成url列表
        url_list = self.get_url_list()
        #2.發送請求
        for url in url_list:
            html_str = self.parse_url(url)
            #3.正則表達式匹配需要的內容
            ret = re.findall(r'title="(.*?)".*?(主演.*?)\n.*?(上映時間.*?)</p>.*?<i class="integer">(\d\.?).*?(\d)</i></p>',html_str,re.S)
            for temp in ret:
                self.rank += 1 # 排名
                print(self.rank, temp)


if __name__ == "__main__":
    maoyantop = MaoYantop()
    maoyantop.run()

部分內容