python 爬虫获取，百度风云榜股票数据，保存csv格式

先看看执行结果 

 

 同路径下会有个 “风云榜.csv” 文件，下面是文件内容

 

 下面是完整代码，复制粘贴就可以运行。有问题请留言。

# -*- coding:utf-8 -*
import requests, csv
from lxml import etree


class baidu(object):
    def __init__(self):
        self.urls = ['http://top.baidu.com/buzz?b=274&c=17&fr=topbuzz_b277_c17',
                     'http://top.baidu.com/buzz?b=277&c=17&fr=topbuzz_b274_c17',
                     'http://top.baidu.com/buzz?b=276&c=17&fr=topbuzz_b277_c17']
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.3945.79 Safari/537.36'}

    def get_all_data(self):
        for url in self.urls:
            response = requests.get(url, headers=self.headers)  # 获取请求
            response.encoding = response.apparent_encoding
            soup = etree.HTML(response.text)
            names = soup.xpath('//a[@class="list-title"]/text()')  # 获取名称
            name_ids = soup.xpath('//td[@class="last"]/span/text()')  # 获取id
            for (name, name_id) in zip(names, name_ids):
                self.Save(name, name_id)

    def Save(self, name, name_id):
        """保存数据"""
        with open('风云榜.csv', 'a', newline='', encoding='utf8') as f:
            spamwriter = csv.writer(f)
            spamwriter.writerow([name, name_id])

    def run(self):
        self.get_all_data()


if __name__ == '__main__':
    fps = baidu()
    fps.run()