python3 파충류https의 구덩이 - 해결됨
9294 단어 python3
# coding=utf-8
import re
import urllib.request
def getHtml(url):
page = urllib.request.urlopen(url)
html = page.read()
html = html.decode('utf-8')
return html
def getImg(html):
reg = r'(.*)
'
img_title = re.compile(reg)
imglist = re.findall(img_title, html)
return imglist
url = "https://tieba.baidu.com"
html = getHtml(url)
imglist = getImg(html)
print(imglist)
/Users/zhu/python3/env/bin/python /Users/zhu/python3/the19/ex3.py
Traceback (most recent call last):
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/urllib/request.py", line 1318, in do_open
encode_chunked=req.has_header('Transfer-encoding'))
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py", line 1239, in request
self._send_request(method, url, body, headers, encode_chunked)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py", line 1285, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py", line 1234, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py", line 1026, in _send_output
self.send(msg)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py", line 964, in send
self.connect()
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py", line 1400, in connect
server_hostname=server_hostname)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/ssl.py", line 407, in wrap_socket
_context=self, _session=session)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/ssl.py", line 814, in __init__
self.do_handshake()
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/ssl.py", line 1068, in do_handshake
self._sslobj.do_handshake()
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/ssl.py", line 689, in do_handshake
self._sslobj.do_handshake()
ssl.SSLError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed (_ssl.c:777)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/Users/zhu/python3/the19/ex3.py", line 21, in
html = getHtml(url)
File "/Users/zhu/python3/the19/ex3.py", line 7, in getHtml
page = urllib.request.urlopen(url)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/urllib/request.py", line 223, in urlopen
return opener.open(url, data, timeout)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/urllib/request.py", line 526, in open
response = self._open(req, data)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/urllib/request.py", line 544, in _open
'_open', req)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/urllib/request.py", line 504, in _call_chain
result = func(*args)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/urllib/request.py", line 1361, in https_open
context=self._context, check_hostname=self._check_hostname)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/urllib/request.py", line 1320, in do_open
raise URLError(err)
urllib.error.URLError: _ssl.c:777)>
Process finished with exit code 1
파충류의 대상은https 링크이기 때문에 ssl 모듈을 가져오면 문제를 해결할 수 있습니다. 마지막 코드는 다음과 같습니다.
# coding=utf-8
import re
import urllib.request
import ssl
def getHtml(url):
page = urllib.request.urlopen(url)
html = page.read()
html = html.decode('utf-8')
return html
def getImg(html):
reg = r'(.*)
'
img_title = re.compile(reg)
imglist = re.findall(img_title, html)
return imglist
ssl._create_default_https_context = ssl._create_unverified_context
url = "https://tieba.baidu.com"
html = getHtml(url)
imglist = getImg(html)
print(imglist)
이 내용에 흥미가 있습니까?
현재 기사가 여러분의 문제를 해결하지 못하는 경우 AI 엔진은 머신러닝 분석(스마트 모델이 방금 만들어져 부정확한 경우가 있을 수 있음)을 통해 가장 유사한 기사를 추천합니다:
Jupyter 공식 DockerHub에 대한 메모에 기재되어 있다. base-notebook minimal-notebook scipy-notebook tensorflow-notebook datascience-notebook pyspark-notebook all-s...
텍스트를 자유롭게 공유하거나 복사할 수 있습니다.하지만 이 문서의 URL은 참조 URL로 남겨 두십시오.
CC BY-SA 2.5, CC BY-SA 3.0 및 CC BY-SA 4.0에 따라 라이센스가 부여됩니다.