pandas爬取表格数据

利用pandas

方法：

1、soup = BeautifulSoup(html.content, ‘lxml’, from_encoding=‘utf-8’)
2、pd.read_html()

请求天气后报的一些表格数据的方法：

#!/usr/bin/env python
# encoding: utf-8

"""
@Time   : 2020/2/15 22:08
@Author : jaden
@Desc   : 利用pandas爬取表格数据 (这种只能拿带有table便签的数据表)
"""
import requests
from bs4 import BeautifulSoup
import pandas as pd

# 1.请求地址url
city_list = ['baotou', 'beijing', 'shanghai']
for city_url in city_list:
    url = 'http://tianqihoubao.com/aqi/' + city_url + '.html'
    headers = {
        'user-agent': '*********************************8'
    }
    html = requests.get(url, headers=headers)
    if html.status_code == 200:
        soup = BeautifulSoup(html.content, 'lxml', from_encoding='utf-8')
        table = soup.find('table', class_='b')
        tf = pd.read_html(table.prettify(), header=0)  # prettify():页面美化（整理成有格式的）
        print(tf[0])
        tf[0].to_csv('results.csv', header=None, encoding='utf-8-sig', mode='a')  # mode = a 持续往进写值
    else:
        print('输出失败')