20231120_python练习_天气网爬取城市近七天温度情况

先根据城市名找到对应编码，然后获取近七天天气情况

淄博 101120301 ['20日（今天）'] ['晴'] <class 'list'> ['7℃'] ['\n', '<3级', '\n']

淄博 101120301 ['21日（明天）'] ['晴转阴'] <class 'list'> ['20℃', '8℃'] ['\n', '<3级', '\n']

淄博 101120301 ['22日（后天）'] ['多云'] <class 'list'> ['17℃', '3℃'] ['\n', '<3级', '\n']

淄博 101120301 ['23日（周四）'] ['晴'] <class 'list'> ['8℃', '-5℃'] ['\n', '3-4级转<3级', '\n']

淄博 101120301 ['24日（周五）'] ['晴转多云'] <class 'list'> ['5℃', '-5℃'] ['\n', '<3级', '\n']

淄博 101120301 ['25日（周六）'] ['阴转多云'] <class 'list'> ['9℃', '0℃'] ['\n', '<3级', '\n']

淄博 101120301 ['26日（周日）'] ['晴'] <class 'list'> ['12℃', '-2℃'] ['\n', '<3级', '\n']

复制代码

import requests
import json
from lxml import etree

city_dic = {}
text_mw = '淄博'
#将中文转置为字符
text_id = str(text_mw.encode('utf-8')).upper().replace('\\X','%')[2:-1]
print('text_id',text_id)

url = 'http://toy1.weather.com.cn/search?cityname=' + text_id
#设置请求头
header={
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36 Edg/117.0.2045.43",
    "Referer":"http://www.weather.com.cn/", 
    "Cookie":"Hm_lvt_080dabacb001ad3dc8b9b9049b36d43b=1700397713; f_city=%E6%B5%8E%E5%8D%97%7C101120101%7C; Hm_lpvt_080dabacb001ad3dc8b9b9049b36d43b=1700398953"
}
resp = requests.get(url=url,headers=header)
print(resp.status_code)

data = resp.text[1:-1]
json_data = json.loads(data)[0]['ref'][0:9]
#获取城市对应编码
print(json_data)
#淄博 101120301
city_url = 'http://www.weather.com.cn/weather/' + json_data + '.shtml'
print(city_url)
city_resp = requests.get(url=city_url,headers=header)
city_resp.encoding = city_resp.apparent_encoding
html = etree.HTML(city_resp.text)
node_all = html.xpath('//ul[@class="t clearfix"]/li')
#print('节点名称',[i.tag for i in node_all])
for node in node_all:
    day_text = node.xpath('.//h1/text()')
    wea_text = node.xpath('.//p[@class="wea"]/text()')
    tem_text = node.xpath('.//p[@class="tem"]//text()')
    for tem in tem_text:
        if tem in ('/','\n'):tem_text.remove(tem)
    win_text = node.xpath('.//p[@class="win"]//text()')
    for win in win_text:
        if win in ('/','\n'):win_text.remove(win)
    print(text_mw,json_data,day_text,wea_text,type(tem_text),tem_text,win_text)