Python爬虫入門実戦------一週間天気予報爬取【転載】【分析なし】

ソース:https://blog.csdn.net/qq_40705355/article/details/83856960

7日間の天気源:http://www.weather.com.cn/weather/101120101.shtml
ソースプログラム

import csv
import urllib.request
from  bs4 import BeautifulSoup
'''      ，     ''' 
#          
url = "http://www.weather.com.cn/weather/101120101.shtml"header = ("User-Agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36")  #       
opener = urllib.request.build_opener()  #       
opener.addheaders = [header]         #      
request = urllib.request.Request(url)   #     
response = urllib.request.urlopen(request)   #          
html = response.read()   #             
html = html.decode('utf-8')    #   utf-8    ，          
 
'''      ，     ''' 
final = []   #       list，             list
bs = BeautifulSoup(html,"html.parser")   #   BeautifulSoup  
body = bs.body  #   body  
data = body.find('div',{'id':'7d'})  #   id 7d div
ul = data.find('ul')  #   ul  
li = ul.find_all('li')  #      li
# print (li)
 
i = 0
for day in li:  #    li          
    if i < 7:
        temp = []
        date = day.find('h1').string #     
#         print (date)
        temp.append(date)  #    temp 
    #     print (temp)
        inf = day.find_all('p')  #   li    p  
    #     print(inf)
    #     print (inf[0])
        temp.append(inf[0].string)  #    p      （    ）  temp 
        if inf[1].find('span') is None:
            temperature_highest = None #                （    ，    ），        ,       
        else:
            temperature_highest = inf[1].find('span').string #       
            temperature_highest = temperature_highest.replace('℃', '') #         ，         ℃
        temperature_lowest = inf[1].find('i').string  #      
        temperature_lowest = temperature_lowest.replace('℃', '')  # #         ℃，      
        temp.append(temperature_highest)
        temp.append(temperature_lowest)
        final.append(temp)
        i = i +1
        
# print(final)
 
with open('weather.csv', 'a', errors='ignore', newline='') as f:
            f_csv = csv.writer(f)
            f_csv.writerows(final)

効果図

自己分析:固定先頭

import csv
import urllib.request
from  bs4 import BeautifulSoup
'''      ，     ''' 
#          
url = "http://www.weather.com.cn/weather/101120101.shtml"
header = ("User-Agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36")  #       
opener = urllib.request.build_opener()  #       
opener.addheaders = [header]         #      
request = urllib.request.Request(url)   #     
response = urllib.request.urlopen(request)   #          
html = response.read()   #             
html = html.decode('utf-8')    #   utf-8    ，          

自己分析じこぶんせき:分析ぶんせき
エレメントを選択すると特に便利です.