Python 3网络爬虫之urllib用法_python3 urllib

# 1. urlopen()
# import urllib.request
# response= urllib.request.urlopen('https://www.python.org')
# print(response.read().decode ('utf-8'))
 
# 1.1 type()
import urllib.request
response = urllib.request.urlopen('https://www.baidu.com')
print(type(response))
# <class 'http.client.HTTPResponse'>
 
# 2 getheaders()
import urllib.request
response = urllib.request.urlopen('https://www.python.org')
print(response.status)
print(response.getheaders())
print(response.getheader('Server'))
 
# 200
# [('Connection', 'close'), ('Content-Length', '49928'), ('Server', 'nginx')]
# nginx
 
# 3 data参数 parse函数
import urllib.parse
import urllib.request
# # 传递了一个参数 word ，值是 hello 它需要被转码成 bytes （字节流）类型
data = bytes(urllib.parse.urlencode({'word': 'hello'}), encoding='utf8')
response = urllib.request.urlopen('http://httpbin.org/post', data=data)
print(response.read())
 
# 4 timeout 参数
import urllib.request
#
response = urllib.request.urlopen('http://httpbin.org/post', timeout=1)
print(response.read())
 
# 5 request方法
import urllib.request
request = urllib.request.Request('https://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': 'Mozilla/4.0 (compatible; MSIE S. S; Windows NT)',
    'Host': 'httpbin.org' }
dict = {
     'name': 'lle'
 }
data = bytes(parse.urlencode(dict), encoding='utf8')
req = request.Request(url=url, data=data, headers=headers, method='POST')
response = request.urlopen(req)
print(response.read().decode('utf-8'))
 
# 6
# HITPDefaultErrorHandler ：用于处理 响应错误，错误都会抛出 HTTP Error 类型的异常
# HTTPRedirectHandler ：用于处理重定向
# HTTPCookieProcessor 用于处理 ki es
# ProxyHandler ：用于设置代理 默认 理为空
# HπPPasswordMgr ：用于管理密码，它维护了用户名和密码的表
# HTTPBasicAut
 
from urllib.request import HTTPPasswordMgrWithDefaultRealm, HTTPBasicAuthHandler, build_opener
from urllib.error import URLError
#
username = 'username'
password = 'password'
url = 'http://localhost:sooo/'
p = HTTPPasswordMgrWithDefaultRealm()
p.add_password(None, url, username, password)
auth_handler = HTTPBasicAuthHandler(p)
opener = build_opener(auth_handler)
try:
   result = opener.open(url)
   html = result.read().decode('utf8')
   print(html)
except URLError as e:
   print(e.reason)
 
# 7 代理配置
from urllib.error import URLError
from urllib.request import ProxyHandler, build_opener
# 
proxy_handler = ProxyHandler({
    ' http': 'http://127.0.0.1:9743 ',
    ' https': 'https://127.0.0.1:9743 '
})
opener = build_opener(proxy_handler)
try:
    response = opener.open('https://www.baidu.com')
    print(response.read().decode('utf-8'))
except URLError as e:
    print(e.reason)
 
# 8 Cookies
import http.cookiejar
import 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)
 
# 9 解析链接 # urlparse 使用
# ，：／／前面的就是 scheme ，代表协议；第一个／符号前面便是 netloc ，即域名，后面是 path ，即访
# 问路径；分号；前面是 params ，代表参数；问号？后面是查询条件 query 般用作 GET 类型的 URL;
# 井号＃后面是锚点，用于直接定位页面内部的下拉位置
from urllib.parse import urlparse
#
result = urlparse('http://www.baidu.com/index.html;user?id=5#comment')
print(type(result), result)
# <class 'urllib.parse.ParseResult'> ParseResult(scheme='http', netloc='www.baidu.com', path='/index.html', params='user', query='id=5', fragment='comment')
 
from urllib.parse import urlparse
#
result = urlparse('www.baidu.com/index.html;user?id=5#comment', scheme='https')
print(result)
ParseResult(scheme='https', netloc='', path='www.baidu.com/index.html', params='user', query='id=5', fragment='comment')
 
 
from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html#comment', allow_fragments=False)
print(result.scheme, result[0], result.netloc, result[1], sep='\n')
# http
# http
# www.baidu.com
# www.baidu.com
 
# 10 urlunparse 用法
from urllib.parse import urlunparse
#
data = ['http', 'www.baidu.com', 'index.html', 'user', 'a=6', 'comment']
print(urlunparse(data))
# http://www.baidu.com/index.html;user?a=6#comment
 
 
# 11 urlsplit() 用法
from urllib.request import urlsplit
result=urlsplit('http://www.baidu.com/index.html;user?id=5#comment')
print(result)
SplitResult(scheme='http', netloc='www.baidu.com', path='/index.html;user', query='id=5', fragment='comment')
 
from urllib.parse import urlsplit
#
result = urlsplit('http://www.baidu.com/index.html;user?id=S#comment')
print(result.scheme, result[0])
# http http
 
# 12 urlunsplit
from urllib.parse import urlunsplit
data = ['http', 'www.baidu.com', 'index.html', 'a=6', 'comment']
print(urlunsplit(data))
# # http://www.baidu.com/index.html?a=6#comment
 
# 13 urlencode用法
from urllib.parse import urlencode
params={
    'name':'germey',
    'age':22
 }
base_url ='http://www.baidu.com?'
url=base_url +urlencode(params)
print(url)
 
# http://www.baidu.com?name=germey&age=22
 
# 14 parse_qs()
from urllib.parse import parse_qs
query='name=germey&age=22'
print(parse_qs(query))
# {'name': ['germey'], 'age': ['22']}
 
# 15 parse_qsl()
from urllib.parse import parse_qsl
query='name=germey&age=22'
print(parse_qsl(query))
# [('name', 'germey'), ('age', '22')]
 
# 16 quote()
from urllib.parse import quote
keyword='壁纸'
url='https://www.baidu.com/s?wd'+quote(keyword)
print(url)
# https://www.baidu.com/s?wd%E5%A3%81%E7%BA%B8
 
# 17 unquote()
from urllib.parse import unquote
# keyword='壁纸'
url='https://www.baidu.com/s?wd='+unquote(keyword)
print(url)
https://www.baidu.com/s?wd=壁纸
 
# set_url()： 用来设置 ro bots txt 文件的链接 如果在创建 RobotFileParser 对象时传入了链
#             接，那么就不需要再使用这个方法设置了
# read()： 读取 robots txt 文件并进行分 注意，这个方法执行一个读取和分析操作，如果不
#          调用这个方法 接下来的判断都会为 False ，所以一定记得调用这个方法 这个方法不会返
#          回任何内容，但是执行了读取操作
# parse()： 用来解析 ro bots. txt 文件，传人的参数是 robots txt 某些行的内 ，它会按照 robots txt
#           的语法规则来分析这些内容
# can_fetch()： 该方法传人两个参数 第一个是 Use r-age nt ，第二个是要抓取的 URL 返回的
#           内容是该搜索引擎是否可以抓取这个 URL ，返回结果是 True False a
# mtime()： 返回的是上次抓取和分析 robots.txt 的时间，这对于长时间分析和抓取的搜索爬虫
#           很有必要的，你可能需要定期检查来抓取最新的 robots.txt
# modified() ：它同样对长时间分析和抓取的搜索爬虫很有帮助，将当前时间设置为上次抓取
#           和分析 robots.txt 的时间
 
from urllib.robotparser import RobotFileParser
#
rp=RobotFileParser()
rp.set_url('http://www.jianshu.com/robots.txt')
rp.read()
print(rp.can_fetch('*','http://www.jianshu.com/p/b67554025d7d'))
print(rp.can_fetch('*','http://www.jianshu.com/search?q=python&page=1&type=collections'))
# False
# False
 
from urllib.robotparser import RobotFileParser
from urllib.request import urlopen
rp=RobotFileParser()
rp.parse(urlopen('http://www.jianshu.com/robots.txt').read().decode('utf-8').split('\n'))
print(rp.can_fetch('*','http://www.jianshu.com/p/b67554025d7d'))
print(rp.can_fetch('*','http://www.jianshu.com/search?q=python&page=1&type=collections'))

代码摘抄之《Python 3网络爬虫开发实战》