清华大佬耗费三个月吐血整理的几百G的资源,免费分享!....>>>
#coding=utf-8 import os import urllib import httplib import requests import json def get_page_content(baseUrl, path, params, headers, type = 'get'): try: httpClient = httplib.HTTPConnection(baseUrl, 80, timeout=30) if type == 'get': httpClient.request('GET', path) response = httpClient.getresponse() print response.status print response.reason print response.read() elif type == 'post': params = urllib.urlencode(params) httpClient.request("POST", path, params, headers) response = httpClient.getresponse() print response.status print response.reason print response.read() print response.getheaders() #获取头信息 else: print 'unsupport' except Exception, e: print Exception, e def get_page_content_by_requests(url, payload, timeout, headers, type = 'get'): try: if type == 'get': response = requests.get(url, params=payload, timeout=timeout) response.encoding = 'gbk' #设定编码 print response.status_code #返回状态 print response.text #返回字符结果 print response.content #返回二进制响应内容 print response.json() #获取Json响应内容 print response.raw #获取原始响应内容 print response.raise_for_status() #非200请况下抛出异常 print response.headers['Content-Type'] #获取响应头某个字段 elif type == 'post': response = requests.post(url, data = json.dumps(payload), headers = headers, timeout=timeout) response.encoding = 'gbk' #设定编码 print response.text else: print 'unsupport' except Exception, e: print Exception, e