pandas.read_html读取表格

qq_187352634

已于 2023-11-21 15:18:30 修改

阅读量83

点赞数

文章标签： pandas html python

于 2023-11-12 18:26:51 首次发布

本文链接：https://blog.csdn.net/qq_37755459/article/details/134363756

版权

pandas.read_html读取表格

import pandas
import requests
from my_fake_useragent import UserAgent

url = "http://tianqi.2345.com/Pc/GetHistory"
def extract_data(year, month):
    params = {
        "areaInfo[areaId]": 71833,
        "areaInfo[areaType]": 2,
        "date[year]": year,
        "date[month]": month
    }
    headers = {"User-Agent": UserAgent().random()}
    resp = requests.get(url, headers=headers, params=params)
    print(resp)
    data = resp.json()["data"]
    df = pandas.read_html(data)[0]
    # print(df.head())
    print("extracting data:", year, month)
    return df
weather_list = []
for year in range(2018, 2021):
    for month in range(1, 13):
        df = extract_data(year, month)
        weather_list.append(df)
pandas.concat(weather_list).to_excel("weatherOfWuHan.xlsx", index=False)
# print(df.head())