Python标准库中提供了：urllib、urllib2、httplib等模块以供Http请求，但是，它的 API 太渣了。它是为另一个时代、另一个互联网所创建的。它需要巨量的工作，甚至包括各种方法覆盖，来完成最简单的任务。
import urllib2 import json import cookielib def urllib2_request(url, method="GET", cookie="", headers={}, data=None): """ :param url: 要请求的url :param cookie: 请求方式，GET、POST、DELETE、PUT.. :param cookie: 要传入的cookie，cookie= 'k1=v1;k1=v2' :param headers: 发送数据时携带的请求头，headers = {'ContentType':'application/json; charset=UTF-8'} :param data: 要发送的数据GET方式需要传入参数，data={'d1': 'v1'} :return: 返回元祖，响应的字符串内容 和 cookiejar对象 对于cookiejar对象，可以使用for循环访问： for item in cookiejar: print item.name,item.value """ if data: data = json.dumps(data) cookie_jar = cookielib.CookieJar() handler = urllib2.HTTPCookieProcessor(cookie_jar) opener = urllib2.build_opener(handler) opener.addheaders.append(['Cookie', 'k1=v1;k1=v2']) request = urllib2.Request(url=url, data=data, headers=headers) request.get_method = lambda: method response = opener.open(request) origin = response.read() return origin, cookie_jar # GET result = urllib2_request('http://127.0.0.1:8001/index/', method="GET") # POST result = urllib2_request('http://127.0.0.1:8001/index/', method="POST", data= {'k1': 'v1'}) # PUT result = urllib2_request('http://127.0.0.1:8001/index/', method="PUT", data= {'k1': 'v1'})
Requests 是使用 Apache2 Licensed 许可证的 基于Python开发的HTTP 库，其在Python内置模块的基础上进行了高度的封装，从而使得Pythoner进行网络请求时，变得美好了许多，使用Requests可以轻而易举的完成浏览器可有的任何操作。
1、GET请求
# 1、无参数实例 import requests ret = requests.get('https://github.com/timeline.json') print ret.url print ret.text # 2、有参数实例 import requests payload = {'key1': 'value1', 'key2': 'value2'} ret = requests.get("http://httpbin.org/get", params=payload) print ret.url print ret.text
向 https://github.com/timeline.json 发送一个GET请求，将请求和响应相关均封装在 ret 对象中。
实例：爬取汽车之家新闻标题、链接和图片
import requests import scrapy from bs4 import BeautifulSoup import os import uuid response = requests.get(url='https://www.autohome.com.cn/news/',) # 用下载自带的编码规则解析 # 也可以指定response.encoding = 'utf-8' response.encoding = response.apparent_encoding # response.status_code 返回的状态码 # lxml性能更好，但需要安装，html.parser是Python内置的 soup = BeautifulSoup(response.text,features='html.parser') tag1 = soup.find(id='auto-channel-lazyload-article') # tag2 = tag1.find('li') # 只找到第一个 tag_list = tag1.find_all('li') # 找到全部，以列表形式输出 for tag in tag_list: tag_a = tag.find('a') if tag_a: # 有a标签的才拿属性 # print(tag_a.attrs.get('href')) # 新闻链接 h3_text = tag_a.find('h3') # 其实是一个对象，只是打印的时候显示文本 # text和string都是获取标签对象的文本 # print(h3_text.string,'*****') # 新闻标题 # print(h3_text.text,'----') # 新闻标题 img_url = tag_a.find('img').attrs.get('src') # print(img_url) # 新闻图片 # 下载图片,.text返回的是文本，.content返回的是字节 # 如果直接写url=img_url，最后会出现http:////p9.pstatp.com/list/pgc-image/153838020 img_response = requests.get("http:" + img_url).content file_name = 'imgs/' + str(uuid.uuid4()) + '.jpg' # with open(file_name,'wb') as f: # f.write(img_response)
2、POST请求
# 1、基本POST实例 import requests payload = {'key1': 'value1', 'key2': 'value2'} ret = requests.post("http://httpbin.org/post", data=payload) print ret.text # 2、发送请求头和数据实例 import requests import json url = 'https://api.github.com/some/endpoint' payload = {'some': 'data'} headers = {'content-type': 'application/json'} ret = requests.post(url, data=json.dumps(payload), headers=headers) print ret.text print ret.cookies
向https://api.github.com/some/endpoint发送一个POST请求，将请求和相应相关的内容封装在 ret 对象中。
3、其他请求
requests.get(url, params=None, **kwargs) requests.post(url, data=None, json=None, **kwargs) requests.put(url, data=None, **kwargs) requests.head(url, **kwargs) requests.delete(url, **kwargs) requests.patch(url, data=None, **kwargs) requests.options(url, **kwargs) # 以上方法均是在此方法的基础上构建 requests.request(method, url, **kwargs)
params={'k1':'v1'} 以GET形式放入URL传到后台的参数
requests模块已经将常用的Http请求方法为用户封装完成，用户直接调用其提供的相应方法即可，其中方法的所有参数有：
def request(method, url, **kwargs): """Constructs and sends a :class:`Request <Request>`. :param method: method for the new :class:`Request` object. :param url: URL for the new :class:`Request` object. :param params: (optional) Dictionary or bytes to be sent in the query string for the :class:`Request`. :param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`. :param json: (optional) json data to send in the body of the :class:`Request`. :param headers: (optional) Dictionary of HTTP Headers to send with the :class:`Request`. :param cookies: (optional) Dict or CookieJar object to send with the :class:`Request`. :param files: (optional) Dictionary of ``'name': file-like-objects`` (or ``{'name': ('filename', fileobj)}``) for multipart encoding upload. :param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth. :param timeout: (optional) How long to wait for the server to send data before giving up, as a float, or a :ref:`(connect timeout, read timeout) <timeouts>` tuple. :type timeout: float or tuple :param allow_redirects: (optional) Boolean. Set to True if POST/PUT/DELETE redirect following is allowed. :type allow_redirects: bool :param proxies: (optional) Dictionary mapping protocol to the URL of the proxy. :param verify: (optional) whether the SSL cert will be verified. A CA_BUNDLE path can also be provided. Defaults to ``True``. :param stream: (optional) if ``False``, the response content will be immediately downloaded. :param cert: (optional) if String, path to ssl client cert file (.pem). If Tuple, ('cert', 'key') pair. :return: :class:`Response <Response>` object :rtype: requests.Response Usage:: >>> import requests >>> req = requests.request('GET', 'http://httpbin.org/get') <Response [200]> """ # By using the 'with' statement we are sure the session is closed, thus we # avoid leaving sockets open which can trigger a ResourceWarning in some # cases, and look like a memory leak in others. with sessions.Session() as session: return session.request(method=method, url=url, **kwargs)
View Code
本文链接：http://task.lmcjl.com/news/6627.html
