我如何解决python web抓取中的urllib错误？

Question

我一直在尝试执行以下代码，但收到以下错误消息：

html = urllib.request.urlopen(url, context=ctx).read()
  File "C:\Program Files (x86)\Microsoft Visual Studio\Shared\Python37_64\lib\urllib\request.py", line 649, in http_error_default
    raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 403: Forbidden

'''

import urllib.request, urllib.parse, urllib.error
from bs4 import BeautifulSoup
import ssl
import sqlite3

# Ignore SSL certificate errors
ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE

url = "http://www.pythonlearn.com/code/mbox.txt"
html = urllib.request.urlopen(url, context=ctx).read()
fh = BeautifulSoup(html, 'html.parser')


#Connecting to the file in which we want to store our db
conn = sqlite3.connect('emaildb.sqlite')
cur = conn.cursor()

#Deleting any possible table that may affect this assignment
cur.execute('''
DROP TABLE IF EXISTS Counts''')

#Creating the table we're going to use
cur.execute('''
CREATE TABLE Counts (org TEXT, count INTEGER)''')



#Reading each line of the file
for line in fh:

    #Finding an email address and splitting it into name and organization
    if not line.startswith('From: ') : continue
    pieces = line.split()
    email = pieces[1]
    (emailname, organization) = email.split("@")
    print (email)

    #Updating the table with the correspondent information
    cur.execute('SELECT count FROM Counts WHERE org = ? ', (organization, ))
    row = cur.fetchone()
    if row is None:
        cur.execute('''INSERT INTO Counts (org, count) 
                VALUES ( ?, 1 )''', ( organization, ) )
    else : 
        cur.execute('UPDATE Counts SET count=count+1 WHERE org = ?', 
            (organization, ))

# We commit the changes after they've finished because this speeds up the 
# execution and, since our operations are not critical, a loss wouldn't suppose
# any problem
conn.commit()

# Getting the top 10 results and showing them
sqlstr = 'SELECT org, count FROM Counts ORDER BY count DESC LIMIT 10'
print ("Counts:")
for row in cur.execute(sqlstr) :
    print (str(row[0]), row[1])

#Closing the DB
cur.close()

'''我不确定出什么问题。

Answer 1

代码没有问题。您是否看到404错误？ 403是另一个错误-参见Wikipedia article。