Python 爬虫，爬取历史天气数据

先上源码

这次用的是BeautifulSoup，解析html,非常的便捷

import datetime
import pandas as pd
import re
import requests
import time
from bs4 import BeautifulSoup

headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36'
}


def get_html(url):
# 这个网站第一次请求一般都会被反爬给挡住，所以要多请求几次
    while True:
        r = requests.get(url, headers=headers)
        print('从', url, '获取数据')
        if 'table' in r.text:
            print('成功获取数据')
            return r.content
        else:
            print('甘霖凉鸡掰，不给我数据')
            time.sleep(1)


def parse_html(page_content):
    soup = BeautifulSoup(page_content, features='lxml')
    table = soup.find('table')
    item_list = table.find_all('tr')

    month = []

    for i in range(1, len(ite