请教各位，python编写爬虫，返回http error 521怎么解决

Question

import urllib.request
import urllib.parse
import urllib.error
import re
import random
def open_url(url):

    req_header = {'Connection': 'Keep-Alive',
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:52.0) Gecko/20100101 Firefox/52.0',
            'Accept':'*/*',
            'Accept-Encoding': 'gzip, deflate',
            'Accept-Language': 'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3'}
    req = urllib.request.Request(url, None, req_header)
    with urllib.request.urlopen(req, None, timeout=5) as respond:
        html = respond.read()
    return html


def get_proxy_urls():
    proxy_list = []
    for i in range(1,11):
        str1 = r'http://www.kuaidaili.com/proxylist/%d/' % i
        proxy_list.append(str1)
    return proxy_list


def get_ip(url):
    comp = '''<td data-title="IP">(.+?)</td>
            <td data-title="PORT">(.+?)</td>
            <td data-title="匿名度">(.+?)</td>
            <td data-title="类型">(.+?)</td>
            <td data-title="get/post支持">(.+?)</td>
            <td data-title="位置">(.+?)</td>
            <td data-title="响应速度">(.+?)</td>
            <td data-title="最后验证时间">(.+?)</td>'''
    text_html = open_url(url).decond('utf_8')
    ip_list = re.findall(comp, text_html)
    return ip_list


def test():
    url = random.choice(get_proxy_urls())
    print(url)
    print(open_url(url))
    print(get_ip(url))
if __name__ == '__main__':
    test()

在urllib.request.urlopen（）处出现异常
urllib.error.HTTPError: HTTP Error 521:

Answer 1

Refer to the blog post https://my.oschina.net/jhao10...
The original blogger used PyV8 to execute JS code, I changed to PyExecJS

import execjs
import re
import requests

url = "http://www.kuaidaili.com/proxylist/1/"

HERDERS = {
    "Host": "www.kuaidaili.com",
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.87 Safari/537.36',
}


def executejs(html):
    # 提取其中的JS加密函数
    js_string = ''.join(re.findall(r'(function .*?)</script>',html))

    # 提取其中执行JS函数的参数
    js_func_arg = re.findall(r'setTimeout\(\"\D+\((\d+)\)\"', html)[0]
    js_func_name = re.findall(r'function (\w+)',js_string)[0]

    # 修改JS函数，使其返回Cookie内容
    js_string = js_string.replace('eval("qo=eval;qo(po);")', 'return po')

    func = execjs.compile(js_string)
    return func.call(js_func_name,js_func_arg)

def parse_cookie(string):
    string = string.replace("document.cookie='", "")
    clearance = string.split(';')[0]
    return {clearance.split('=')[0]: clearance.split('=')[1]}

# 第一次访问获取动态加密的JS
first_html = requests.get(url=url,headers=HERDERS).content.decode('utf-8')

# 执行JS获取Cookie
cookie_str = executejs(first_html)

# 将Cookie转换为字典格式
cookie = parse_cookie(cookie_str)
print('cookies = ',cookie)

# 带上cookies参数，再次请求
response = requests.get(url=url,headers=HERDERS,cookies=cookie)
print(response.status_code)

Answer 2

It should be the anti-crawling mechanism of the website. You can check out this article about scrapy encountering 521

The specific situation still depends on the anti-crawling strategy of the specific target. If it doesn’t work, just use their proxy to crawl their proxy 2333333333

Answer 3

There was a problem with the added cookie. It was fixed after fixing it. Thank you