爬虫札记1_requests+xlwt+lxml 爬取maoyan

```

import json
from lxml import etree
import requests
import xlwt


class MaoyanSpider:
    # 通过建立一个类，多个函数 实现

    # 代码实现通过lxml和xpath对猫眼电影top100的爬取

    # 保存成TXT和Excel表格中

    
    # 初始化url和headers
    def __init__(self):
        self.start_url = 'https://maoyan.com/board/4?offset={}'
        self.headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36'}
        
    
    # 根据url的规律，构造url_list
    def get_url_list(self):
        url_list = [self.start_url.format(10*i) for i in range(10)]
        return url_list
      
    # 发送请求，获取响应
    def parse_url(self, url):
        print("parsing...", url)
        response = requests.get(url=url, headers=self.headers)
        return response.content.decode('utf-8', 'ignore')
    
    # 获取数据
    def get_content_list(self, html_str):
        html = etree.HTML(html_str)
        div_list = html.xpath('//*[@id="app"]/div/div/div[1]/dl/dd')
        content_list = []
        for div in div_list:
                item = {'film_name': '', 'film_actor': '', 'film_time': ''}
                item["film_name"] = div.xpath('.//div/div/div[1]/p[1]/a/text()')[0].strip('[]')
                item["film_actor"] = div.xpath('.//div/div/div[1]/p[2]/text()')[0].replace('\n ', '').strip().split("主演：")[1]    # 取出来的数据先去掉换行再去掉空格最后去掉主演：
                item["film_time"] = div.xpath('.//div/div/div[1]/p[3]/text()')[0].strip('[]').split("上映时间：")[1]
                content_list.append(item)
                
        return content_list

    # 保存数据
    def save_content_list(self, content_list):
        with open("maoyan2.txt", "a", encoding="utf-8") as f :
            for content in content_list:
                f.write(json.dumps(content, ensure_ascii=False))
                f.write("\n")
                
        print("保存成功")
        
    # 数据保存到Excel中，使用xlwt（用于写入Excel中）
    def save_to_excel(self, content_list):
        workbook = xlwt.Workbook(encoding='utf-8')
        sheet = workbook.add_sheet('maoyan_film') # 设置表名
        head = ['电影名称','主演','上映时间']  # 设置表头
        for h in range(len(head)):
            sheet.write(0, h, head[h])

        length = len(content_list)
        for j in range(1,length+1):
            sheet.write(j,0,content_list[j-1]["film_name"])
            sheet.write(j,1,content_list[j-1]["film_actor"])
            sheet.write(j,2,content_list[j-1]["film_time"])

        workbook.save('./maoyan2.xls')
        print('写入Excel成功')
    
        
    def main(self):
        # 获得url_list
        url_list = self.get_url_list()
        # 在url_list中进行请求的发送，内容的获取以及保存数据
        content_lists = []
        for url in url_list:
            html_str = self.parse_url(url)
            content_list = self.get_content_list(html_str)
            # extend()将两个列表进行合并;append()是在末尾进行追加元素
            self.save_content_list(content_list)
            content_lists.extend(content_list)
        self.save_to_excel(content_lists)
                
if __name__ == '__main__':
    maoyan = MaoyanSpider()
    maoyan.main()
   ```