基本Get請求:
#-*- coding:utf-8 -*-import requests url = 'www.baidu.com'r = requests.get(url)print r.text
帶參數Get請求:
#-*- coding:utf-8 -*-import requests url = 'http://www.baidu.com'payload = {'key1': 'value1', 'key2': 'value2'} r = requests.get(url, params=payload)print r.text
POST請求模擬登陸及一些回傳物件的方法:
#-*- coding:utf-8 -*-import requests url1 = 'www.exanple.com/login'#登陆地址url2 = "www.example.com/main"#需要登陆才能访问的地址data={"user":"user","password":"pass"} headers = { "Accept":"text/html,application/xhtml+xml,application/xml;", "Accept-Encoding":"gzip", "Accept-Language":"zh-CN,zh;q=0.8", "Referer":"www.example.com/", "User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36" } res1 = requests.post(url1, data=data, headers=headers) res2 = requests.get(url2, cookies=res1.cookies, headers=headers)print res2.conten
t#取得二進位回應內容print res2.raw#取得原始回應內容,需要stream=Trueprint res2.raw.read(50)print type(res2.text)#回傳解碼成unicode的內容print res2.urlprint res2.history#追蹤重定向print res2. cookiesprint res2.cookies['example_cookie_name']print res2.headersprint res2.headers['Content-Type']print res2.headers.get('content-type')print res2.json#講回內容編碼為jsonprint res2.encoding #返回內容編碼print res2.status_code#傳回http狀態碼print res2.raise_for_status()#傳回錯誤狀態碼
使用Session()物件的寫法(Prepared Requests):
#-*- coding:utf-8 -*-import requests s = requests.Session() url1 = 'www.exanple.com/login'#登陆地址url2 = "www.example.com/main"#需要登陆才能访问的地址data={"user":"user","password":"pass"} headers = { "Accept":"text/html,application/xhtml+xml,application/xml;", "Accept-Encoding":"gzip", "Accept-Language":"zh-CN,zh;q=0.8", "Referer":"http://www.example.com/", "User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36" } prepped1 = requests.Request('POST', url1, data=data, headers=headers ).prepare() s.send(prepped1)''' 也可以这样写 res = requests.Request('POST', url1, data=data, headers=headers ) prepared = s.prepare_request(res) # do something with prepped.body # do something with prepped.headers s.send(prepared) '''prepare2 = requests.Request('POST', url2, headers=headers ).prepare() res2 = s.send(prepare2)print res2.content
另一種寫法:
#-*- coding:utf-8 -*-import requestss = requests.Session()url1 = 'www.exanple.com/login'#登陆地址url2 = "www.example.com/main"#需要登陆才能访问的页面地址data={"user":"user","password":"pass"}headers = { "Accept":"text/html,application/xhtml+xml,application/xml;", "Accept-Encoding":"gzip", "Accept-Language":"zh-CN,zh;q=0.8", "Referer":"http://www.example.com/", "User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36" }res1 = s.post(url1, data=data)res2 = s.post(url2)print(resp2.content) SessionApi 其他的一些请求方式 >>> r = requests.put("http://httpbin.org/put")>>> r = requests.delete("http://httpbin.org/delete")>>> r = requests.head("http://httpbin.org/get")>>> r = requests.options("http://httpbin.org/get")
遇到的問題:
在cmd下執行,遇到小錯誤:
UnicodeEncodeError:'gbk' codec can' t encode character u'\xbb' in position 23460: illegal multibyte sequence
分析:
1、Unicode是編碼還是解碼
UnicodeEncodeError
#-*- coding:utf-8 -*-import requests url = 'www.baidu.com'r = requests.get(url)print r.encoding >utf-8已經確定html的字串是utf-8的,則可以直接去通過utf-8去編碼。 print r.text.encode('utf-8')
#
以上是Python利用Requests庫寫爬蟲的實例詳解的詳細內容。更多資訊請關注PHP中文網其他相關文章!