思路分析
分别爬取八大地区的城市最低气温,再合起来即可得到全国各个城市的最低气温。
由于每一个地区的页面布局基本一致,因此,我们只要完成其中一个地区的数据提取,并写一个函数封装起来,对于其他地区,传入相应参数循环调用此函数即可。
本文数据提取使用的是BeautifulSoup,用XPath定位也可以。具体操作比较简单,就是请求对应页面,提取想要的数据,然后保存数据。完整的代码如下所示。
完整代码
# !/usr/bin/env python
# —*— coding: utf-8 —*—
# @Time: 2020/2/3 9:56
# @Author: Martin
# @File: weather.py
# @Software:PyCharm
import requests
import pandas as pd
from bs4 import BeautifulSoup
def main():
urls = {
'http://www.weather.com.cn/textFC/hb.shtml',
'http://www.weather.com.cn/textFC/db.shtml',
'http://www.weather.com.cn/textFC/hd.shtml',
'http://www.weather.com.cn/textFC/hz.shtml',
'http://www.weather.com.cn/textFC/hn.shtml',
'http://www.weather.com.cn/textFC/xb.shtml',
'http://www.weather.com.cn/textFC/xn.shtml',
'http://www.weather.com.cn/textFC/gat.shtml'
}
weather_data = []
for url in urls:
weather_data += parse_page(url)
save(weather_data)
def save(data):
pd.DataFrame(data).to_csv('./result/weather.csv', index=False, encoding='utf_8_sig')
def parse_page(url):
headers = {
'Referer': 'http://www.weather.com.cn/textFC/hb.shtml',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36'
}
data = []
response = requests.get(url, headers=headers)
text = response.content.decode('utf-8')
soup = BeautifulSoup(text, 'html5lib')
divs = soup.find_all('div', class_='conMidtab2')
for div in divs:
tbodys = div.find_all('tbody')
for tbody in tbodys:
trs = tbody.find_all('tr')[2:]
for index, tr in enumerate(trs):
tds = tr.find_all('td')
if index == 0:
city_name = list(tds[1].stripped_strings)[0]
else:
city_name = list(tds[0].stripped_strings)[0]
min_temperature = int(list(tds[-2])[0])
print({'city_name': city_name, 'min_temperature': min_temperature})
data.append({'city_name': city_name, 'min_temperature': min_temperature})
return data
if __name__ == '__main__':
main()
结果展示