iPhone6刚出的时候,移动官网有个每满十万送一台iPhone,当时用这个小爬虫自动爬,快到十万的时候打开浏览器(这个版本好像没加这个功能),哈哈,现在用不了,这篇从我扣扣空间(那时我还年少,只知道QQ)转过来的,扣扣空间显示代码太糟糕了,迁过来,里面有句不错设置本地编码,转码使用urllib2和cookeie,json等要素的小爬虫,还是有点参考价值。
# -*- coding: utf-8 -*- import sys import urllib2 import cookielib import json import time url = "http://service.js.10086.cn/act_js/activity_web/1319/home.html" getNumUrl = "http://service.js.10086.cn/cmp_service/actionDispatcher.do" # 添加 cookie 到 urllib2 cj = cookielib.LWPCookieJar() cookie_support = urllib2.HTTPCookieProcessor(cj) opener = urllib2.build_opener(cookie_support, urllib2.HTTPHandler) urllib2.install_opener(opener) # 伪装成浏览器的头, 移动真蛋疼检测浏览器的 headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36', 'Origin': 'http://service.js.10086.cn', 'Referer': 'http://service.js.10086.cn/act_js/activity_web/1319/index.html?WT.mc_ev=1412RRHB_JL'} req = urllib2.Request(url, headers=headers) urllib2.urlopen(req) type = sys.getfilesystemencoding() # 设置本地编码 # 打印第一访问的网页 #content = urllib2.urlopen(req).read() # print content.decode("UTF-8").encode(type) # convert encode format # 请求参数 postData = """jsonParam=[{"activityCode":"1319","dynamicURI":"doubleAct","dynamicParameter":{"method":"queryUserLoginInfo","actStageCode":"1319"},"dynamicDataNodeName":"API_queryUserLoginInfo_doubleAct","dynamicPriority":1}] """ request = urllib2.Request(getNumUrl, postData, headers) response = urllib2.urlopen(request) text = response.read() nextNum = int(json.loads(text)[ "API_queryUserLoginInfo_doubleAct"]["resultObj"]["nextNum"]) max = 0 print "下一轮上限", nextNum, "万, 计数中最后一百进行倒计时" while True: response = urllib2.urlopen(request) text = response.read() # print text.decode("UTF-8").encode(type) num = int(json.loads(text)[ "API_queryUserLoginInfo_doubleAct"]["resultObj"]["fnum"]) if num > max: max = num print max if num > nextNum * 10000: # 大于某个上限后停止 break elif num > nextNum * 10000 - 100: # 最后一百个加速 time.sleep(0.1) elif num > nextNum * 10000 - 500: time.sleep(0.5) elif num > nextNum * 10000 - 1000: time.sleep(1) else: time.sleep(3)