Python爬虫（二）

学习Python爬虫过程中的心得体会以及知识点的整理，方便我自己查找，也希望可以和大家一起交流。

—— requests库应用详解相关代码 ——

1.

import requestsurl = 'https://account.tophant.com/login.html?response_type=code&client_id=b611bfe4ef417dbc&state=2e509c092de6ba1bf39a6fff76dd9a76'#requests的请求方法:get、post、put、delete、head、options等r = requests.get(url)r = requests.post(url,data=xxx)r = requests.put(url)r = requests.delete(url)r = requests.head(url)r = requests.options(url)#代理认证：proxies = {
     "http": "http://127.0.0.1:8080",  "https": "http://127.0.0.1:8080",}proxies = {
       "http": "http://user:pass@10.10.1.10:3128/",}#查看响应码print r.status_code#重定向r = requests.get(url, allow_redirects=False)print r.history#查看相应内容print r.textprint r.content#修改系统默认编码格式import sysreload(sys)sys.setdefaultencoding('utf-8')#查看请求头print r.request.headers#查看请求参数print r.request.body#查看响应头print r.headers#保存返回的结果fh = open("abc.png", 'w')fh.write(r.content)fh.close()#查看返回的编码格式print r.encoding#更改返回的编码格式r.encoding = "utf-8"#添加header头headers = {
   'user-agent': 'my-aasdasdaspp/0.0.1', 'asd':'hello world!'}#修改cookiecookies = dict(cookies_are='working')#获得响应头中的cookieprint r.cookies['domain']#如何发送post请求payload = {
   'name': 'loop', 'age': '12'}r = requests.post("http://httpbin.org/post", data=payload)#设置超时r = requests.get(url, timeout=5)r = requests.get(url, timeout=None)#使用sessionconn = requests.session()r = conn.get(url)print r.request.headersr = conn.get(url)print r.request.headers#请求方法r = requests.post(url, proxies=proxies, headers=headers, cookies=cookies, verify=False, data=payload)

转载地址：http://wbazi.baihongyu.com/

你可能感兴趣的文章