Python | 中国天气网+数据分析

最新推荐文章于 2024-02-29 10:42:48 发布

Lindbergh_

最新推荐文章于 2024-02-29 10:42:48 发布

阅读量1.1k

点赞数

本文链接：https://blog.csdn.net/Lin_Bolun/article/details/112135765

版权

一、数据获取

数据连接

http://www.tianqihoubao.com/lishi/

在这里插入图片描述

获取某个城市2011年至今每天的数据

import requests
from lxml import etree
import pandas as pd
import os
import re


class Weather:
    def __init__(self, city):
        self.city = city
        self.host_url = "http://www.tianqihoubao.com/lishi/{}/month/{}.html"
        self.url = "http://www.tianqihoubao.com/lishi/{}.html".format(self.city)
        self.headers = {
   
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36"
        }

    def get_url(self, url):
        response = requests.get(url, headers=self.headers)
        html_str = response.text
        return html_str

    def get_month_url_list(self, html_str):
        html = etree.HTML(html_str)
        url_list = [i for i in html.xpath("//div[@id='content']/div/ul/li/a/@href")]
        return url_list

    def get_content_list(self, html_str):
        content_list = list()
        html = etree.HTML(html_str)
        tr_list = html.xpath("//*[@id='content']/table/tr")
        for tr in tr_list[1:]:
            item = dict()
            item["日期"] = tr.xpath("./td[1]/a/@href")[0