python爬虫学习のurllibライブラリ

5758 ワード

urlopen

getタイプのページ：

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

postタイプのページ：

import urllib.request
import urllib.parse
data=bytes(urllib.parse.urlencode({'word':'hello'}),encoding='utf-8')
response = urllib.request.urlopen("http://httpbin.org/post",data=data)# http     
print(response.read())

タイムアウト

import urllib.request

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

応答
ステータスコード、レスポンスヘッダ

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")

Request

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")

import urllib.request

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

ハードラー

エージェント

from urllib import request,parse
url = "http://httpbin.org/post"
headers = {
    'User-Agent':'Mozilla/4.0(compatible;MSIE ;Windows NT)',
    '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','Mozilla/4.0(compatible;MSIE ;Windows NT)')
response = request.urlopen(req)
print(response.read().decode('utf-8'))

cookie（検査-appication）

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://www.baidu.com")
print(response.read())

保存

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)

読み込み

import http.cookiejar,urllib.request
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)

異常処理

import http.cookiejar,urllib.request
cookie = http.cookiejar.MozillaCookieJar()
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'))

良い書き方：

from urllib import request,error
try:
    response = request.urlopen("http://www.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='
')
except error.URLError as e:  #       
    print(e.reason)
else :
    print("Request Successfully")

URL解析

urlparse

import socket
import urllib.request
import urllib.error

try:
    response = urllib.request.urlopen('http://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")

urlunparse

from urllib.parse import urlparse

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

urljon

from urllib.parse import urlunparse

data = ['http','www.baidu.com','index.html','user','a=6','comment']
print(urlunparse(data))

urlencode

from urllib.parse import urljoin

print(urljoin('http://www.baidu.com','FAQ.html'))#      ，      http(s)

Junnitはどのように一つの方法だけを実行しますか？

Cハハハ並列プログラミング【from msdn】