Question

我写了一个小python脚本，这是我的python脚本。

#! /usr/bin/python3

import notify2
import requests,bs4,pprint
import time


while True:

        respond=requests.get('https://cricbuzz.com')
        soup=bs4.BeautifulSoup(respond.text,'html.parser')
        element = soup.find_all('div', {'class': 'cb-col cb-col-25 cb-mtch-blk'})


        for match in element:
            if 'IND' in match.getText():
                pprint.pprint(match.getText())
                break


        notify2.init('app name')
        n = notify2.Notification("Match Score",
                             match.getText(),
                             "notification-message-im"
                            )
        n.show()
        time.sleep(int(60*2))

使用Beautiful Soup模块接收请求并解析HTML，该模块在其中运行两分钟并继续运行。它工作正常，但低于下面的值突然发生了错误，不知道为什么吗？我的笔记本电脑的互联网连接良好。

错误：

Traceback (most recent call last):
  File "/home/chaitu/.local/lib/python3.6/site-packages/urllib3/connectionpool.py", line 600, in urlopen
    chunked=chunked)
  File "/home/chaitu/.local/lib/python3.6/site-packages/urllib3/connectionpool.py", line 343, in _make_request
    self._validate_conn(conn)
  File "/home/chaitu/.local/lib/python3.6/site-packages/urllib3/connectionpool.py", line 849, in _validate_conn
    conn.connect()
  File "/home/chaitu/.local/lib/python3.6/site-packages/urllib3/connection.py", line 356, in connect
    ssl_context=context)
  File "/home/chaitu/.local/lib/python3.6/site-packages/urllib3/util/ssl_.py", line 359, in ssl_wrap_socket
    return context.wrap_socket(sock, server_hostname=server_hostname)
  File "/usr/lib/python3.6/ssl.py", line 407, in wrap_socket
    _context=self, _session=session)
  File "/usr/lib/python3.6/ssl.py", line 814, in __init__
    self.do_handshake()
  File "/usr/lib/python3.6/ssl.py", line 1068, in do_handshake
    self._sslobj.do_handshake()
  File "/usr/lib/python3.6/ssl.py", line 689, in do_handshake
    self._sslobj.do_handshake()
ConnectionResetError: [Errno 104] Connection reset by peer

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/chaitu/.local/lib/python3.6/site-packages/requests/adapters.py", line 445, in send
    timeout=timeout
  File "/home/chaitu/.local/lib/python3.6/site-packages/urllib3/connectionpool.py", line 638, in urlopen
    _stacktrace=sys.exc_info()[2])
  File "/home/chaitu/.local/lib/python3.6/site-packages/urllib3/util/retry.py", line 367, in increment
    raise six.reraise(type(error), error, _stacktrace)
  File "/home/chaitu/.local/lib/python3.6/site-packages/urllib3/packages/six.py", line 685, in reraise
    raise value.with_traceback(tb)
  File "/home/chaitu/.local/lib/python3.6/site-packages/urllib3/connectionpool.py", line 600, in urlopen
    chunked=chunked)
  File "/home/chaitu/.local/lib/python3.6/site-packages/urllib3/connectionpool.py", line 343, in _make_request
    self._validate_conn(conn)
  File "/home/chaitu/.local/lib/python3.6/site-packages/urllib3/connectionpool.py", line 849, in _validate_conn
    conn.connect()
  File "/home/chaitu/.local/lib/python3.6/site-packages/urllib3/connection.py", line 356, in connect
    ssl_context=context)
  File "/home/chaitu/.local/lib/python3.6/site-packages/urllib3/util/ssl_.py", line 359, in ssl_wrap_socket
    return context.wrap_socket(sock, server_hostname=server_hostname)
  File "/usr/lib/python3.6/ssl.py", line 407, in wrap_socket
    _context=self, _session=session)
  File "/usr/lib/python3.6/ssl.py", line 814, in __init__
    self.do_handshake()
  File "/usr/lib/python3.6/ssl.py", line 1068, in do_handshake
    self._sslobj.do_handshake()
  File "/usr/lib/python3.6/ssl.py", line 689, in do_handshake
    self._sslobj.do_handshake()
urllib3.exceptions.ProtocolError: ('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "./score.py", line 10, in <module>
    respond=requests.get('https://cricbuzz.com')
  File "/home/chaitu/.local/lib/python3.6/site-packages/requests/api.py", line 72, in get
    return request('get', url, params=params, **kwargs)
  File "/home/chaitu/.local/lib/python3.6/site-packages/requests/api.py", line 58, in request
    return session.request(method=method, url=url, **kwargs)
  File "/home/chaitu/.local/lib/python3.6/site-packages/requests/sessions.py", line 512, in request
    resp = self.send(prep, **send_kwargs)
  File "/home/chaitu/.local/lib/python3.6/site-packages/requests/sessions.py", line 622, in send
    r = adapter.send(request, **kwargs)
  File "/home/chaitu/.local/lib/python3.6/site-packages/requests/adapters.py", line 495, in send
    raise ConnectionError(err, request=request)
requests.exceptions.ConnectionError: ('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))

Answer 1

我用这个功能来抓取 Youtube 的喜欢和不喜欢。它提供了对 241 个链接的访问，它们会再次访问并从我离开的地方抓取更多。尝试/排除和延长睡眠时间，您将能够比现在刮得更多。此外，如果您想解决这个问题，您可以使用某些代理或 VPN 来不断更改您的 IP，这样请求就不会来自同一个 IP 地址。

def scrape_info(url):

    result = {}

    session = HTMLSession()

    try:
        response = session.get(url)
        # execute Java-script
        response.html.render(sleep=40)
        # create bs object to parse HTML
        soup = bs(response.html.html, "html.parser")


        # number of likes
        x = soup.find_all("yt-formatted-string", {"id": "text", "class": "ytd-toggle-button-renderer"})
        if x is not None and len(x) > 0:
            result["likes"] = x[0].text
            result["dislikes"] = x[1].text
        else:
            result["likes"] = None
            result["dislikes"] = None
    except requests.exceptions.ConnectionError:
        print("Connection refused")
        result["likes"] = None
        result["dislikes"] = None
        time.sleep(30)


    return result

长时间运行脚本时出现ConnectionError

1 个答案: