问用Python实现HTML的with抓取

EN

import requests
from bs4 import BeautifulSoup as bs

url = 'http://some.local.domain/'

response = requests.get(url)
soup = bs(response.text, 'html.parser')

# let's get title of the page
title = soup.title
print(title)

# let's get all the links in the page
links = soup.find_all('a')
for link in links:
    print(link.get('href'))
    link1 = link[0]
    link2 = link[1]

# let's follow a link we find in the page (we'll go for the first)
response = requests.get(link1, stream=True)
# if we have an image and we want to download it 
if response.status_code == 200:
    with open(url.split('/')[-1], 'wb') as f:
        for chunk in response:
            f.write(chunk)

# if the link is another web page
response = requests.get(link2)
soup = bs(response.text, 'html.parser')

# let's get title of the page
title = soup.title
print(title)