欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页  >  IT编程

Python爬虫之Urllib库的基本使用

程序员文章站 2022-06-24 14:14:42
urllib提供的功能就是利用程序去执行各种HTTP请求。如果要模拟浏览器完成特定功能,需要把请求伪装成浏览器。伪装的方法是先监控浏览器发出的请求,再根据浏览器的请求头来伪装,User-Agent头就是用来标识浏览器的。 ......
# get请求
import urllib.request
response = urllib.request.urlopen("http://www.baidu.com")
print(response.read().decode('utf-8'))

# post请求
import urllib.parse
import urllib.request
data = bytes(urllib.parse.urlencode({"word":"hello"}), encoding='utf8')
response = urllib.request.urlopen('http://httpbin.org/post', data=data)
print(response.read())

import urllib.request
response = urllib.request.urlopen('http://httpbin.org/get', timeout=1)
print(response.read())

import socket
import urllib.request
import urllib.error
try:
    response = urllib.request.urlopen('http://httpbin.org/get', timeout = 0.1)
except urllib.error.urlerror as e:
    if isinstance(e.reason, socket.timeout):
        print('time out')

# 响应类型
import urllib.request
response = urllib.request.urlopen('http://www.python.org')
print(type(response))

# 状态码、响应头
import urllib.request
response = urllib.request.urlopen('http://www.python.org')
print(response.status)
print(response.getheaders())
print(response.getheader('server'))

# request
import urllib.request
request = urllib.request.request('http://python.org')
response = urllib.request.urlopen(request)
print(response.read().decode('utf-8'))

from urllib import request, parse
url = 'http://httpbin.org/post'
headers = {
    'user-agent': 'user-agent: mozilla/5.0 (windows nt 10.0; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/70.0.3538.102 safari/537.36',
    'host':'httpbin.org'
}
dict = {
    'name':'germey'
}
data = bytes(parse.urlencode(dict), encoding = 'utf-8')
req = request.request(url = url, data = data, headers = headers, method = 'post')
response = request.urlopen(req)
print(response.read().decode('utf-8'))

from urllib import request, parse
url = 'http://httpbin.org/post'
dict = {
    'name': 'germey'
}
data = bytes(parse.urlencode(dict), encoding = 'utf-8')
req = request.request(url = url, data = data, method = 'post')
req.add_header('user-agent', 'user-agent: mozilla/5.0 (windows nt 10.0; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/70.0.3538.102 safari/537.36')
response = request.urlopen(req)
print(response.read().decode('utf-8'))

#代理
import urllib.request
proxy_handler = urllib.request.proxyhandler({
    'http': 'http://127.0.0.1:9743',
    'https': 'https://127.0.0.1:9743'
})
opener = urllib.request.build_opener(proxy_handler)
response = opener.open('http://httpbon.org/get')
print(response.read())

# cookie
import http.cookiejar, urllib.request
cookie = http.cookiejar.cookiejar()
handler = urllib.request.httpcookieprocessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
for item in cookie:
    print(item.name + " = " + item.value)

# 保存cookie为1.txt
import http.cookiejar, urllib.request
filename = '1.txt'
cookie = http.cookiejar.mozillacookiejar(filename)
handler = urllib.request.httpcookieprocessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
cookie.save(ignore_discard = true, ignore_expires = true)

# 另外一种方式保存cookie
import http.cookiejar, urllib.request
filename = '1.txt'
cookie = http.cookiejar.lwpcookiejar(filename)
handler = urllib.request.httpcookieprocessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
cookie.save(ignore_discard = true, ignore_expires = true)

# 读取cookie
import http.cookiejar, urllib.request
cookie = http.cookiejar.lwpcookiejar()
cookie.load('1.txt', ignore_discard = true, ignore_expires = true)
handler = urllib.request.httpcookieprocessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
print(response.read().decode('utf-8'))

# 异常处理
from urllib import request, error
try:
    response = request.urlopen('http://lidonghao.com')
except error.urlerror as e:
    print(e.reason)

from urllib import request, error
try:
    response = request.urlopen('http://www.baidu.com/101')
except error.httperror as e:
    print(e.reason, e.code, sep = '\n')
except error.urlerror as e:
    print(e.reason)
else:
    print('request successfully')

import socket
import urllib.request
import urllib.error
try:
    response = urllib.request.urlopen("https://www.baidu.com", timeout = 0.01)
except urllib.error.urlerror as e:
    print(type(e.reason))
    if isinstance(e.reason, socket.timeout):
        print("time out")
 1 # 解析url
 2 # urlparse
 3 from urllib.parse import urlparse
 4 result = urlparse('http://www.baidu.com/index.html;user?id=5#comment')
 5 print(type(result), result)
 6 
 7 from urllib.parse import urlparse
 8 result = urlparse('www.baidu.com/index.html;user?id=5#comment', scheme = "https")
 9 print(result)
10 
11 from urllib.parse import urlparse
12 result = urlparse('http://www.baidu.com/index.html;user?id=5#comment', scheme = "https")
13 print(result)
14 
15 from urllib.parse import urlparse
16 result = urlparse('http://www.baidu.com/index.html;user?id=5#comment', allow_fragments = false)
17 print(result)
18 
19 from urllib.parse import urlparse
20 result = urlparse('http://www.baidu.com/index.html#comment', allow_fragments = false)
21 print(result)
 1 # urlunparse
 2 from urllib.parse import urlunparse
 3 data = ['http', 'www.baidu.com', 'index,html', 'user', 'a=6', 'comment']
 4 print(urlunparse(data))
 5 
 6 # urljoin
 7 from urllib.parse import urljoin
 8 print(urljoin('http://www.baidu.com', 'faq.html'))
 9 print(urljoin('http://www.baidu.com', 'https://cuiqingcai.com/faq.html'))
10 print(urljoin('http://www.baidu.com/about.html', 'https://cuiqingcai.com/faq.html'))
11 print(urljoin('http://www.baidu.com/about.html', 'http://cuiqingcai.com/faq.html?question=2'))
12 print(urljoin('http://www.baidu.com?wd=abc', 'https://cuiqingcai.com/index.php'))
13 print(urljoin('http://www.baidu.com', '?category=2#comment'))
14 print(urljoin('www.baidu.com', '?category=2#comment'))
15 print(urljoin('www.baidu.com#comment', '?category=2'))
16 
17 # urlencode
18 from urllib.parse import urlencode
19 params = {
20     'name':'germey',
21     'age':22
22 }
23 base_url = 'http://www.baidu.com'
24 url = base_url + urlencode(params)
25 print(url)