py自動車の家を這い出すニュースケース
1176 ワード
import requests
from bs4 import BeautifulSoup
response = requests.get("https://www.autohome.com.cn/news/")
# 1. content /text
# print(response.content) # content
response.encoding = 'gbk'
# print(response.text) # text
soup = BeautifulSoup(response.text,'html.parser')
# tag = soup.find(id='auto-channel-lazyload-article') # ,
# h3 = tag.find(name='h3',class_ ='') # class ,
# h3 = tag.find(name='h3',attrs= {'class':''}) #
# print(h3)
#
li_list = soup.find(id='auto-channel-lazyload-article').find_all(name='li')
for li in li_list:
title = li.find('h3') #
if not title:# null,
continue
title = title.text
summary = li.find("p").text
url = li.find("a").get('href')
img = li.find("img").get('src')
print(img)
#
res = requests.get(img)
file_name = "%s.jpg"%(title,)
with open(file_name,'wb') as f:
f.write(res.content) #
もっと素晴らしい文章は王明昌のブログに注目してください.