爬虫（二）：Urllib库详解

# urllib参数urllib.request.urlopen(url, data=None, [timeout, ]*, cafile=None, capath=None, cadefault=False, context=None) # url ?post数据 ?超时#############################import urllib.request# GET方式（不加data）response = urllib.request.urlopen(‘http://www.baidu.com‘) # 请求数据print(response.read().decode(‘utf-8‘)) # 转换为字符串编码，read()得到的是byte格式的#############################import urllib.parseimport urllib.request# POST方式（加data）data = bytes(urllib.parse.urlencode({‘word‘: ‘hello‘}), encoding=‘utf8‘)response = urllib.request.urlopen(‘http://httpbin.org/post‘, data=data) ?# http://httpbin.org/post 用来做HTTP测试的网址print(response.read())#############################import urllib.request#超时设置response = urllib.request.urlopen(‘http://httpbin.org/get‘, timeout=1)print(response.read())##############################

# 响应类型import urllib.requestresponse = urllib.request.urlopen(‘https://www.python.org‘)print(type(response)) #<class ‘http.client.HTTPResponse‘>############################## 状态码、响应头import urllib.requestresponse = urllib.request.urlopen(‘https://www.python.org‘)print(response.status) #获取状态码print(response.getheaders()) # 获取响应头print(response.getheader(‘Server‘)) # 响应的服务#############################import urllib.request#获取响应内容response = urllib.request.urlopen(‘https://www.python.org‘)print(response.read().decode(‘utf-8‘)) # read() 获取bytes类型

# 加入headers，发送一个POST请求from urllib import request, parseurl = ‘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‘)req = request.Request(url=url, data=data, headers=headers, method=‘POST‘)response = request.urlopen(req)print(response.read().decode(‘utf-8‘))

# 添加代理import urllib.requestproxy_handler = urllib.request.ProxyHandler({ # 代理设置 ???‘http‘: ‘http://127.0.0.1:9743‘, ???‘https‘: ‘https://127.0.0.1:9742‘})opener = urllib.request.build_opener(proxy_handler)response = opener.open(‘http://httpbin.org/get‘)print(response.read())

import http.cookiejar, urllib.request# 获取cookiescookie = 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)############################## 将cookie保存为txt文件import http.cookiejar, urllib.requestfilename = ‘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)############################## 读取cookie文件import http.cookiejar, urllib.request# 用哪种格式存cookies，就用哪种方法读取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‘))

# 异常处理1from urllib import request, errortry: ???response = request.urlopen(‘http://cuiqingcai.com/index.htm‘)except error.URLError as e: ???print(e.reason)############################## 异常处理2from urllib import request, errortry: ???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‘)############################## 异常处理3import socketimport urllib.requestimport urllib.errortry: ???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‘)

# 一个参数from urllib.parse import urlparseresult = urlparse(‘http://www.baidu.com/index.html;user?id=5#comment‘)print(type(result), result)########################### 指定协议, 如果没有取https, 有就用url带的from urllib.parse import urlparseresult = urlparse(‘http://www.baidu.com/index.html;user?id=5#comment‘, scheme=‘https‘) # 指定协议类型print(result)########################### allow_fragments=False 一般不会用,把锚链接部分移动到参数(没有参数在往前移动#XXXX)from urllib.parse import urlparseresult = urlparse(‘http://www.baidu.com/index.html#comment‘, allow_fragments=False)print(result)

from urllib.parse import urlunparse# 拼接网站data = [‘http‘, ‘www.baidu.com‘, ‘index.html‘, ‘user‘, ‘a=6‘, ‘comment‘]print(urlunparse(data)) #http://www.baidu.com/index.html;user?a=6#comment

from urllib.parse import urljoin# 拼接print(urljoin(‘http://www.baidu.com‘, ‘Faq.html‘))# 以第二个位基准print(urljoin(‘http://www.baidu.com‘, ‘https://www.baidu.com/aaa‘))# 拼接print(urljoin(‘http://www.baidu.com‘, ‘?a=1‘))

# 参数化get参数from urllib.parse import urlencodeparams = { ???‘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