每天一個爬蟲練習，爬取天氣資料，適合新手-有解無憂

前言
每天一個爬蟲練習，爬個比較簡單的網站
import requests
from bs4 import BeautifulSoup
import pandas as pd
import time
def get_data(url):
    resp = requests.get(url)

    html = resp.content.decode('gbk')

    soup = BeautifulSoup(html, 'html.parser')
    tr_list = soup.find_all('tr')

    dates, conditions, tempmin, tempmax = [], [], [], []
    for data in tr_list[1:]:
        sub_data = data.text.split()

        dates.append(sub_data[0])
        conditions.append(''.join(sub_data[1:3]))
        tempmax.append(sub_data[3])
        tempmin.append(sub_data[5])
    _data = pd.DataFrame()
    _data["日期"] = dates
    _data['天氣狀況'] = conditions
    _data['最高氣溫'] = tempmax
    _data['最低氣溫'] = tempmin

    return _data

#data_1_month = get_data('此處為任一月份資料的網址') 使用時只需修改此處，具體示例如下


print('正在抓取1月份資料')
data_1_month = get_data('http://www.tianqihoubao.com/lishi/huichang/month/201101.html')
print('正在抓取2月份資料')
data_2_month = get_data('http://www.tianqihoubao.com/lishi/huichang/month/201102.html')
print('正在抓取3月份資料')
data_3_month = get_data('http://www.tianqihoubao.com/lishi/huichang/month/201103.html')
print('正在抓取4月份資料')
data_4_month = get_data('http://www.tianqihoubao.com/lishi/huichang/month/201104.html')
print('正在抓取5月份資料')
data_5_month = get_data('http://www.tianqihoubao.com/lishi/huichang/month/201105.html')
print('正在抓取6月份資料')
data_6_month = get_data('http://www.tianqihoubao.com/lishi/huichang/month/201106.html')
print('正在抓取7月份資料')
data_7_month = get_data('http://www.tianqihoubao.com/lishi/huichang/month/201107.html')
print('正在抓取8月份資料')
data_8_month = get_data('http://www.tianqihoubao.com/lishi/huichang/month/201108.html')
print('正在抓取9月份資料')
data_9_month = get_data('http://www.tianqihoubao.com/lishi/huichang/month/201109.html')
print('正在抓取10月份資料')
data_10_month = get_data('http://www.tianqihoubao.com/lishi/huichang/month/201110.html')
print('正在抓取11月份資料')
data_11_month = get_data('http://www.tianqihoubao.com/lishi/huichang/month/201111.html')
print('正在抓取12月份資料')
data_12_month = get_data('http://www.tianqihoubao.com/lishi/huichang/month/201112.html')


print('資料抓取成功！正在整合該年資料，請稍后......')
time.sleep(3)

data = pd.concat([data_1_month, data_2_month, data_3_month, data_4_month, data_5_month, data_6_month, data_7_month, data_8_month, data_9_month, data_10_month, data_11_month, data_12_month]).reset_index(drop=True)
print(data)

print('資料整合完畢!')
#資料爬取結果會保存在此代碼同一徑下
示例結果：
轉載請註明出處，本文鏈接：https://www.uj5u.com/houduan/33690.html
標籤：Python
上一篇：requests模塊
下一篇：javascript