from bs4 import BeautifulSoup
import urllib.request
r = urllib.request.urlopen('http://www.aflcio.org/Legislation-and-Politics/Legislative-Alerts').read()
soup = BeautifulSoup(r)
print type(soup)
我收到消息“urllib.error.HTTPError:HTTP Error 403:Forbidden”
在模块方面,我是一个完全的初学者,所以我不知道我在做什么。遗憾。
答案 0 :(得分:0)
您可能想要指定UserAgent:
import requests
from bs4 import BeautifulSoup
ret = requests.request(
'GET',
'http://www.aflcio.org/Legislation-and-Politics/Legislative-Alerts',
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6) AppleWebKit/602.4.8 (KHTML, like Gecko) Version/10.0.3 Safari/602.4.8'}
)
soup = BeautifulSoup(ret.text, "html.parser")
print type(soup)