这是使用 BeautifulSoup 和 httplib2 (以及基于证书的身份验证)的解决方案:
import BeautifulSoup
import httplib2
def meta_redirect(content):
soup = BeautifulSoup.BeautifulSoup(content)
result=soup.find("meta",attrs={"http-equiv":"Refresh"})
if result:
wait,text=result["content"].split(";")
if text.strip().lower().startswith("url="):
url=text.strip()[4:]
return url
return None
def get_content(url, key, cert):
h=httplib2.Http(".cache")
h.add_certificate(key,cert,"")
resp, content = h.request(url,"GET")
# follow the chain of redirects
while meta_redirect(content):
resp, content = h.request(meta_redirect(content),"GET")
return content
使用 requests 和 lxml 库的类似解决方案。还做了一个简单的检查,确保被测试的东西实际上是 HTML(我的实现中的一个要求)。还能够通过使用请求库的会话来捕获和使用 cookie(如果重定向 + cookie 被用作反抓取机制,有时是必要的)。
import magic
import mimetypes
import requests
from lxml import html
from urlparse import urljoin
def test_for_meta_redirections(r):
mime = magic.from_buffer(r.content, mime=True)
extension = mimetypes.guess_extension(mime)
if extension == '.html':
html_tree = html.fromstring(r.text)
attr = html_tree.xpath("//meta[translate(@http-equiv, 'REFSH', 'refsh') = 'refresh']/@content")[0]
wait, text = attr.split(";")
if text.lower().startswith("url="):
url = text[4:]
if not url.startswith('http'):
# Relative URL, adapt
url = urljoin(r.url, url)
return True, url
return False, None
def follow_redirections(r, s):
"""
Recursive function that follows meta refresh redirections if they exist.
"""
redirected, url = test_for_meta_redirections(r)
if redirected:
r = follow_redirections(s.get(url), s)
return r
用途:
s = requests.session()
r = s.get(url)
# test for and follow meta redirects
r = follow_redirections(r, s)
好吧,似乎没有库支持它,所以我一直在使用这段代码:
import urllib2
import urlparse
import re
def get_hops(url):
redirect_re = re.compile('<meta[^>]*?url=(.*?)["\']', re.IGNORECASE)
hops = []
while url:
if url in hops:
url = None
else:
hops.insert(0, url)
response = urllib2.urlopen(url)
if response.geturl() != url:
hops.insert(0, response.geturl())
# check for redirect meta tag
match = redirect_re.search(response.read())
if match:
url = urlparse.urljoin(url, match.groups()[0].strip())
else:
url = None
return hops
如果你不想使用bs4,你可以像这样使用lxml:
from lxml.html import soupparser
def meta_redirect(content):
root = soupparser.fromstring(content)
result_url = root.xpath('//meta[@http-equiv="refresh"]/@content')
if result_url:
result_url = str(result_url[0])
urls = result_url.split('URL=') if len(result_url.split('url=')) < 2 else result_url.split('url=')
url = urls[1] if len(urls) >= 2 else None
else:
return None
return url
我想提供此处编写的代码的更新版本。考虑到 urlparse 不适用于 Python 3 并且已被 urllib.parse 取代,我已经针对 Python 3.10+ 进行了自己的调整,但也删除了 httplib2/urllib2 并转而支持 requests。请理解,我合并了此处已有帖子中的代码并进行了修改以创建更新的答案,这只是一个协作更新,而不是我自己的工作。
import requests as re
from bs4 import BeautifulSoup
from urllib.parse import urljoin
def meta_redirect(content):
soup = BeautifulSoup(content.text.lower(), features='html.parser')
result=soup.find("meta", attrs={"http-equiv":"refresh"})
if result:
wait, text=result["content"].split(";")
if text.strip().lower().startswith("url="):
url=text.strip()[4:].replace("'","")
if not url.startswith('http'):
url = urljoin(content.url, url)
return url
return None
def get_content(url):
content = re.get(url, verify=False)
# follow the chain of redirects
while meta_redirect(content):
content = re.get(meta_redirect(content), verify=False)
return content
def main():
url = 'put your url here that has meta redirects'
source = get_content(url)
# This will print the source of the website
print(source.text)
使用BeautifulSoup或lxml来解析HTML。