Python-正则表达式-天气爬虫-存储到CSV文件

爬取的网址为http://www.tianqihoubao.com/lishi/chengdu/month/201802.html。

在用正则表达式爬取时，要注意对换行符的处理。

import csv
import re
import requests
import time

def urlPool():
    '''构建url池'''
    urlList = []
    for i in range(1, 13):
        if i < 10:
        #   %字符串的替换
            urlList.append('http://www.tianqihoubao.com/lishi/chengdu/month/20180%s.html' % i)
        else:
            urlList.append('http://www.tianqihoubao.com/lishi/chengdu/month/2018%s.html' % i)
    return urlList

def getHtml(url):
    '''构造请求url函数，返回html文本'''
    try:
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
        }
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return response.text
    except reques