實例：python爬取某地歷史天氣預報

實現目標：爬取某地歷史天氣情況（以深圳2019年爲例）
需要的庫：requests，bs4，pandas
PS：requests 和 bs4 庫很小，大概150K左右
第一步：
找目標url；

第二步：獲取網頁源代碼

url = 'http://www.tianqihoubao.com/lishi/shenzhen/month/201901.html'
req = requests.get(url)
html = req.text

第三步：數據提取，提取自己需要的內容

soup = BeautifulSoup(html,'html.parser')  
tr_list = soup.find_all('tr')
datas,condition,temp = [], [], []
for data in tr_list[1:]:
    sub_data = data.text.split()
    a = sub_data[0].replace('年','/')#將年月日用'/'代替，此處可省略，看個人需求
    b = a.replace('月','/')
    c = b.replace('日', '')
    datas.append(c)
    condition.append(''.join(sub_data[1:3]))
    temp.append(''.join(sub_data[3:6]))

打印效果如下：

第四步：保存數據

_data = pd.DataFrame()   # 創建一個表格
_data['日期'] = datas  #向表格內添加數據
_data['天氣狀況'] = condition
_data['溫度'] = temp
_data.to_csv('深圳2019.01天氣記錄.csv',index=False, encoding='utf-8')

效果如下：

如下是一個月和多個月的整體代碼。

import requests
from bs4 import BeautifulSoup
import pandas as pd

'''====================================深圳2019.1歷史天氣數據======================================'''
# 目標url
url = 'http://www.tianqihoubao.com/lishi/shenzhen/month/201901.html'
# 獲取網頁源代碼
req = requests.get(url)
html = req.text
soup = BeautifulSoup(html,'html.parser') 
tr_list = soup.find_all('tr')
datas,condition,temp = [], [], []
for data in tr_list[1:]:
    sub_data = data.text.split()
    a = sub_data[0].replace('年','/')
    b = a.replace('月','/')
    c = b.replace('日', '')
    datas.append(c)
    condition.append(''.join(sub_data[1:3]))
    temp.append(''.join(sub_data[3:6]))
# 數據保存
_data = pd.DataFrame()   # 創建一個表格
_data['日期'] = datas  #向表格內添加數據
_data['天氣狀況'] = condition
_data['溫度'] = temp
_data.to_csv('深圳2019.01天氣記錄.csv',index=False, encoding='utf-8')

'''====================================深圳2019 1——4月的歷史天氣數據======================================'''

# 獲取url
def get_data(url):
    req = requests.get(url)
    html = req.text
    # 數據提取
    soup = BeautifulSoup(html,'html.parser')  
    tr_list = soup.find_all('tr')
    datas,condition,temp = [], [], []
    for data in tr_list[1:]:
        sub_data = data.text.split()
        # print(sub_data)
        a = sub_data[0].replace('年','/')
        b = a.replace('月','/')
        c = b.replace('日', '')
        datas.append(c)
        condition.append(''.join(sub_data[1:3]))
        temp.append(''.join(sub_data[3:6]))
    # 數據保存
    _data = pd.DataFrame()   # 創建一個表格
    _data['日期'] = datas  #向表格內添加數據
    _data['天氣狀況'] = condition
    _data['溫度'] = temp
    # print(_data)
    return _data

data_01 = get_data('http://www.tianqihoubao.com/lishi/shenzhen/month/201901.html')
data_02 = get_data('http://www.tianqihoubao.com/lishi/shenzhen/month/201902.html')
data_03 = get_data('http://www.tianqihoubao.com/lishi/shenzhen/month/201903.html')
data_04 = get_data('http://www.tianqihoubao.com/lishi/shenzhen/month/201904.html')

data = pd.concat([data_01,data_02,data_03,data_04]).reset_index(drop=True)
data.to_csv('深圳2019.01-04月天氣記錄.csv',index=False, encoding='utf-8')