Python爬虫之Urllib库的基本使用

Posted 2021-01-22 凌冷

# 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 = ‘
‘)
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)