Share ten methods of py3 crawling web resources

In the past two days, I have learned how to use python3 to crawl web resources and found many methods, so I will add a few notes today.

In the past two days, I have learned how to use python3 to crawl web resources, and found many methods, so I will add a few notes today.

1. The simplest

import urllib.request
response = urllib.request.urlopen('http://python.org/')
html = response.read()

2. Use Request

import urllib.request
 
req = urllib.request.Request('http://python.org/')
response = urllib.request.urlopen(req)
the_page = response.read()

3. Send data

#! /usr/bin/env python3
 
import urllib.parse
import urllib.request
 
url = 'http://localhost/login.php'
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
values = {
     'act' : 'login',
     'login[email]' : 'yzhang@i9i8.com',
     'login[password]' : '123456'
     }
 
data = urllib.parse.urlencode(values)
req = urllib.request.Request(url, data)
req.add_header('Referer', 'http://www.python.org/')
response = urllib.request.urlopen(req)
the_page = response.read()
 
print(the_page.decode("utf8"))

4. Send data and header

#! /usr/bin/env python3
 
import urllib.parse
import urllib.request
 
url = 'http://localhost/login.php'
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
values = {
     'act' : 'login',
     'login[email]' : 'yzhang@i9i8.com',
     'login[password]' : '123456'
     }
headers = { 'User-Agent' : user_agent }
 
data = urllib.parse.urlencode(values)
req = urllib.request.Request(url, data, headers)
response = urllib.request.urlopen(req)
the_page = response.read()
 
print(the_page.decode("utf8"))

5, http error

#! /usr/bin/env python3
 
import urllib.request
 
req = urllib.request.Request('http://www.python.org/fish.html')
try:
  urllib.request.urlopen(req)
except urllib.error.HTTPError as e:
  print(e.code)
  print(e.read().decode("utf8"))

6, exception handling 1

#! /usr/bin/env python3
 
from urllib.request import Request, urlopen
from urllib.error import URLError, HTTPError
req = Request("http://twitter.com/")
try:
  response = urlopen(req)
except HTTPError as e:
  print('The server couldn\'t fulfill the request.')
  print('Error code: ', e.code)
except URLError as e:
  print('We failed to reach a server.')
  print('Reason: ', e.reason)
else:
  print("good!")
  print(response.read().decode("utf8"))

7, exception handling 2

#! /usr/bin/env python3
 
from urllib.request import Request, urlopen
from urllib.error import URLError
req = Request("http://twitter.com/")
try:
  response = urlopen(req)
except URLError as e:
  if hasattr(e, 'reason'):
    print('We failed to reach a server.')
    print('Reason: ', e.reason)
  elif hasattr(e, 'code'):
    print('The server couldn\'t fulfill the request.')
    print('Error code: ', e.code)
else:
  print("good!")
  print(response.read().decode("utf8"))

8, HTTP authentication

#! /usr/bin/env python3
 
import urllib.request
 
# create a password manager
password_mgr = urllib.request.HTTPPasswordMgrWithDefaultRealm()
 
# Add the username and password.
# If we knew the realm, we could use it instead of None.
top_level_url = "https://cms.tetx.com/"
password_mgr.add_password(None, top_level_url, 'yzhang', 'cccddd')
 
handler = urllib.request.HTTPBasicAuthHandler(password_mgr)
 
# create "opener" (OpenerDirector instance)
opener = urllib.request.build_opener(handler)
 
# use the opener to fetch a URL
a_url = "https://cms.tetx.com/"
x = opener.open(a_url)
print(x.read())
 
# Install the opener.
# Now all calls to urllib.request.urlopen use our opener.
urllib.request.install_opener(opener)
 
a = urllib.request.urlopen(a_url).read().decode('utf8')
print(a)

9. Use proxy

#! /usr/bin/env python3
 
import urllib.request
 
proxy_support = urllib.request.ProxyHandler({'sock5': 'localhost:1080'})
opener = urllib.request.build_opener(proxy_support)
urllib.request.install_opener(opener)

 
a = urllib.request.urlopen("http://g.cn").read().decode("utf8")
print(a)

10. Timeout

#! /usr/bin/env python3
 
import socket
import urllib.request
 
# timeout in seconds
timeout = 2
socket.setdefaulttimeout(timeout)
 
# this call to urllib.request.urlopen now uses the default timeout
# we have set in the socket module
req = urllib.request.Request('http://twitter.com/')
a = urllib.request.urlopen(req).read()
print(a)

[Related recommendations]

1. Python Free Video Tutorial

2. Python Learning Manual

3. Marco Education Python Basic Grammar Full Explanation Video

The above is the detailed content of Share ten methods of py3 crawling web resources. For more information, please follow other related articles on the PHP Chinese website!