python爬蟲的urllib庫詳解

1.什麼是Urllib

python内置的HTTP請求庫

   urllib.request 請求子產品

   urllib.error 異常處理子產品

   urllib.parse url解析子產品

   urllib.robotparser robots.txt 解析子產品

2.相對于Python2的變化

Python2

import urllib2

response = urllib2.urlopen(“

http://www.baidu.com

”)

Python3

import urllib.request

response = urllib.request.urlopen(“

3.urllib用法講解

3.1urlopen

urllib.request.urlopen(url, data=None, [timeout, ]*, cafile=None, capath=None, cadefault=False, context=None)

3.1.1實作網頁get請求

import urllib.request
response = urllib.request.urlopen('http://www.baidu.com')
print(response.read().decode('utf-8'))
      

3.1.2 請求時加載資料

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())      

3.1.3逾時請求設定

#逾時請求設定
import urllib.request
response = urllib.request.urlopen('http://httpbin.org/get', timeout=1)
print(response.read())      

3.1.4判斷逾時請求

#判斷逾時請求
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')      

3.2響應

3.2.1響應類型

import urllib.request
response = urllib.request.urlopen('https://www.baidu.com')
print(type(response))      

3.2.2狀态碼、響應頭

import urllib.request
response = urllib.request.urlopen('https://www.baidu.com')
print(response.status)#狀态碼
print(response.getheaders())#所有顯示頭
print(response.getheader('Server'))      

import urllib.request
response = urllib.request.urlopen('https://www.baidu.com')
print(response.read().decode('utf-8'))  #網頁的源代碼      

3.3Request

3.3.1使用Request來請求網頁

import urllib.request
request = urllib.request.Request('https://www.baidu.com')
response = urllib.request.urlopen(request)
print(response.read().decode('utf-8'))      

3.3.2通過Request請求參數來請求網頁

from urllib import request, parse
# 通過這是請求參數來請求網頁
url = 'http://httpbin.org/post'
headers = {
    'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)',
    'Host': 'httpbin.org'
}
dict = {
    'name': 'Germey'
}
data = bytes(parse.urlencode(dict), encoding='utf8') #formdata
req = request.Request(url=url, data=data, headers=headers, method='POST')
response = request.urlopen(req)
print(response.read().decode('utf-8'))      

3.3.2通過Request.add_header方法來請求網頁

from urllib import request, parse

url = 'http://httpbin.org/post'
dict = {
    'name': 'Germey'
}
data = bytes(parse.urlencode(dict), encoding='utf8')
req = request.Request(url=url, data=data, method='POST')
#通過Request.add_header方法來請求網頁
req.add_header('User-Agent', 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)')
response = request.urlopen(req)
print(response.read().decode('utf-8'))      

3.4Handler

3.4.1代理:使用代理，來僞裝IP位址

#handler相當于一個額外的工具，來處理一些設定
import urllib.request
#使用代理，來僞裝IP位址
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://httpbin.org/get')
print(response.read())      

3.4.2Cookie:cookies用來維持登入狀态

import http.cookiejar, urllib.request
#cookies用來維持登入狀态
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)      

import http.cookiejar, urllib.request
#cookies儲存成文本檔案，儲存格式mozilla
filename = "cookie.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)      

import http.cookiejar, urllib.request
#cookies儲存成文本檔案，儲存格式lwp
filename = 'cookie.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)      

import http.cookiejar, urllib.request
#讀取cookies
cookie = http.cookiejar.LWPCookieJar()
cookie.load('cookie.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'))      

3.5異常處理

3.5.1讀出異常

from urllib import request, error
try:
    response = request.urlopen('http://cuiqingcai.com/index.htm')
except error.URLError as e:
    print(e.reason)      

from urllib import request, error

try:
    response = request.urlopen('http://cuiqingcai.com/index.htm')
except error.HTTPError as e:
    print(e.reason, e.code, e.headers, 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')      

3.6URL解析

3.6.1urlparse：将網址拆分成不同意義的字典

urllib.parse.urlparse(urlstring, scheme=’’, allow_fragments=True)

#網址，協定類型，錨點連結

from urllib.parse import urlparse
#解析網址
result = urlparse('http://www.baidu.com/index.html;user?id=5#comment')
print(type(result), result)      

from urllib.parse import urlparse

result = urlparse('www.baidu.com/index.html;user?id=5#comment', scheme='https')
print(result)      

from urllib.parse import urlparse

result = urlparse('http://www.baidu.com/index.html;user?id=5#comment', scheme='https')
print(result)      

from urllib.parse import urlparse

result = urlparse('http://www.baidu.com/index.html;user?id=5#comment', allow_fragments=False)
print(result)      

from urllib.parse import urlparse

result = urlparse('http://www.baidu.com/index.html#comment', allow_fragments=False)
print(result)      

3.6.2urlunparse：urlparse的反編譯

from urllib.parse import urlunparse
#urlparse的反函數
data = ['http', 'www.baidu.com', 'index.html', 'user', 'a=6', 'comment']
print(urlunparse(data))      

3.6.3urljoin：拼接網址

from urllib.parse import urljoin
#用來拼接url
print(urljoin('http://www.baidu.com', 'FAQ.html'))
print(urljoin('http://www.baidu.com', 'https://cuiqingcai.com/FAQ.html'))
print(urljoin('http://www.baidu.com/about.html', 'https://cuiqingcai.com/FAQ.html'))
print(urljoin('http://www.baidu.com/about.html', 'https://cuiqingcai.com/FAQ.html?question=2'))
print(urljoin('http://www.baidu.com?wd=abc', 'https://baidu.com/index.php'))
print(urljoin('http://www.baidu.com', '?category=2#comment'))
print(urljoin('www.baidu.com', '?category=2#comment'))
print(urljoin('www.baidu.com#comment', '?category=2'))      

3.6.4urlencode：把一個字典對象轉換成get請求參數

from urllib.parse import urlencode
#把一個字典對象轉換成get請求參數
params = {
    'name': 'germey',
    'age': 22
}
base_url = 'http://www.baidu.com?'
url = base_url + urlencode(params)
print(url)