爬蟲-鏈接驗證
@(Python)[python]
鏈接驗證
編寫一個程序,對給定的網頁URL,下載該頁面所有鏈接的頁面。程序應該標記出所有具有404“Not Found”狀態碼的頁面,將它們作爲壞鏈接輸出。
import requests
import bs4
url = 'http://ifeve.com/'
response = requests.get(url)
soup = bs4.BeautifulSoup(response.text, "lxml")
a_list = soup.select('a')
for a in a_list:
a_url = a.get('href')
try:
response = requests.get(a_url)
if response.status_code == requests.codes.not_found:
print("Page %s is broken link" % a_url)
else:
print("Page %s is other type link" % a_url)
response.raise_for_status()
except:
print("Page %s is Error" % a_url)