Olá,
Quando tento rodar o programa no PyCharm (eu instalei o bs4 e urllib nele) ele retorna o erro abaixo: Traceback (most recent call last): File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/urllib/request.py", line 1319, in do_open h.request(req.get_method(), req.selector, req.data, headers, File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/http/client.py", line 1230, in request self.sendrequest(method, url, body, headers, encode_chunked) File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/http/client.py", line 1276, in sendrequest self.endheaders(body, encode_chunked=encode_chunked) File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/http/client.py", line 1225, in endheaders self.sendoutput(message_body, encode_chunked=encode_chunked) File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/http/client.py", line 1004, in sendoutput self.send(msg) File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/http/client.py", line 944, in send self.connect() File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/http/client.py", line 1399, in connect self.sock = self.context.wrapsocket(self.sock, File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/ssl.py", line 500, in wrap_socket return self.sslsocket_class.create( File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/ssl.py", line 1040, in _create self.dohandshake() File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/ssl.py", line 1309, in do_handshake self.sslobj.dohandshake() ssl.SSLCertVerificationError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1108)
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "/Users/fabio/PycharmProjects/web_scraping/testes.py", line 14, in response = urlopen(url) File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/urllib/request.py", line 222, in urlopen return opener.open(url, data, timeout) File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/urllib/request.py", line 525, in open response = self.open(req, data) File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/urllib/request.py", line 542, in _open result = self.call_chain(self.handle_open, protocol, protocol + File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/urllib/request.py", line 502, in callchain result = func(*args) File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/urllib/request.py", line 1362, in https_open return self.do_open(http.client.HTTPSConnection, req, File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/urllib/request.py", line 1322, in do_open raise URLError(err) urllib.error.URLError: <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1108)>
import bs4
import urllib.request as urllib_request
import pandas
print("BeautifulSoup ->", bs4.__version__)
print("urllib ->", urllib_request.__version__)
print("pandas ->", pandas.__version__)
from urllib.request import urlopen
from bs4 import BeautifulSoup
url = 'https://alura-site-scraping.herokuapp.com/hello-world.php'
response = urlopen(url)
html = response.read()
soup = BeautifulSoup(html, 'html.parser')
print(soup.find('h1', id="hello-world").get_text())
print(soup.find('p').get_text())
