爬虫day6
关于<https://www.aqistudy.cn/html/city_detail.html 中国空气质量在线监测分析平台
js加密和混淆的解析
刚开始是的日期没有,加载,是因为已经加载完了,换一个日期.
可以看到数据是动态加载的
但是数据加密了
post请求,而且请求的数据也加密了
可能是谷歌浏览器的js没有监听,所以换比较好用的火狐浏览器
事件监听
getData请求数据
找到element(谷歌浏览器)(定义处) 可以看到执行了getAQI和getweather
function getWeatherData()
{
var method = 'GETCITYWEATHER';
var param = {};
param.city = city;
param.type = type;
param.startTime = startTime;
param.endTime = endTime;
getServerData(method, param, function(obj) {
data = obj.data;
if(data.total>0)
{
dataTemp.splice(0, dataTemp.length);
dataHumi.splice(0, dataHumi.length);
dataWind.splice(0, dataWind.length);
for(i=0;i<data.rows.length;i++)
{
dataTemp.push({
x: converTimeFormat(data.rows[i].time).getTime(),
y: parseInt(data.rows[i].temp)
});
dataHumi.push({
x: converTimeFormat(data.rows[i].time).getTime(),
y: parseInt(data.rows[i].humi)
});
dataWind.push({
x: converTimeFormat(data.rows[i].time).getTime(),
y: parseInt(data.rows[i].wse),
d: data.rows[i].wd,
w: data.rows[i].tq,
marker:{symbol: getWindDirectionUrl(data.rows[i].wd)}
});
}
state ++ ;
if(state>=2)
{
showCurrentTab();
}
}
}, 0.5);
}以及在搜索里找到getWeather ,有4个参数method, param, function(obj) ,0.5
中间的是function函数参数 以及getServerData 后面的0.5);说明是在调用函数
去找getServerData函数定义处
又是乱码...加密了,不对,是混淆了,
到解密平台去解密一下: <http://www.bm8.com.cn/jsConfusion/
object = city type starttime endtime 等 进行md5加密
url 对php那个文件发送请求,获得动态的数据
自己写一个 假的函数去调用获得 param请求参数
function getPostParamCode(method, city, type, startTime, endTime){
var param = {};
param.city = city;
param.type = type;
param.startTime = startTime;
param.endTime = endTime;
return getParam(method, param);
}然后通过这个参数 发送post 爬取内容
代码如下: 将字符串转换成js代码
import requests
# 补充
import execjs
node = execjs.get()
# Params
method = 'GETDETAIL'
city = '北京'
type = 'HOUR'
start_time = '2018-01-25 00:00:00'
end_time = '2018-01-25 23:00:00'
# Compile javascript
file = 'jsCode.js'
ctx = node.compile(open(file, encoding='utf-8').read())
# Get params
js = 'getPostParamCode("{0}","{1}","{2}","{3}","{4}")'.format(method, city, type, start_time, end_time)
params = ctx.eval(js)
url = 'https://www.aqistudy.cn/apinew/aqistudyapi.php'
data = {
'd': params
}
page_text = requests.post(url, data=data).text
js = 'decodeData("{0}")'.format(page_text)
decrypted_data = ctx.eval(js)
# print(js)
print(decrypted_data)
然后在通过decodeData 解密 获取最终数据
params
tdgHOYxwKdDSgYXe+RLPzYCgLvrddahasI5XXklB4gVLYqab+XRPpMD/oSqnJ/aEmFwzVEUhLnPzRy03+X1BIzLvxQKwu4A3YsqR3OemYgNnHqPdBwvJlbxia99YeK+xhYnh+pXoudhbw1bJHi/H1n7o0PGXMb60NrW7f/Yd0Y+H4hNSDHVYyZnBsxJh6kkarSTzqNharSCvztTU3b95na/jKrVddatUdH5CVexOuKjxjdT0C1swsJBH7bdn3Sga7wXZ20GcktH39BwkMaScAudbM3yYSgDrJkCmV4i6ZZlU54+aR4MY7r7J9IpW1TSy93gC24xTvjiaa5Apo2c77/b7gcIiTvSc14c2AnLDI5oOfgIl4J2hRMFfqr4g4Lfuq1cRlOQg5c5uZrQjyIsIFicregIDGNu4fluOdSLC+Pg+OQDMIlqLzHtwgZ2MW0HuoL8o/copcJu1ClHTCk0y+g==
decrypted_data
{"success":true,"errcode":0,"errmsg":"success","result":{"success":true,"data":{"total":24,"rows":[{"time":"2018-01-25 00:00:00","aqi":"43","pm2_5":"29","pm10":"43","co":"0.7","no2":"56","o3":"23","so2":"6","rank":null},{"time":"2018-01-25 01:00:00","aqi":"25","pm2_5":"15","pm10":"25","co":"0.6","no2":"45","o3":"34","so2":"6","rank":null},{"time":"2018-01-25 02:00:00","aqi":"25","pm2_5":"9","pm10":"25","co":"0.5","no2":"38","o3":"39","so2":"5","rank":null},{"time":"2018-01-25 03:00:00","aqi":"22","pm2_5":"9","pm10":"22","co":"0.5","no2":"40","o3":"37","so2":"5","rank":null},{"time":"2018-01-25 04:00:00","aqi":"16","pm2_5":"8","pm10":"15","co":"0.5","no2":"32","o3":"45","so2":"4","rank":null},{"time":"2018-01-25 05:00:00","aqi":"16","pm2_5":"8","pm10":"14","co":"0.4","no2":"25","o3":"51","so2":"4","rank":null},{"time":"2018-01-25 06:00:00","aqi":"17","pm2_5":"7","pm10":"15","co":"0.4","no2":"24","o3":"53","so2":"4","rank":null},{"time":"2018-01-25 07:00:00","aqi":"18","pm2_5":"5","pm10":"18","co":"0.4","no2":"26","o3":"52","so2":"3","rank":null},{"time":"2018-01-25 08:00:00","aqi":"19","pm2_5":"5","pm10":"19","co":"0.4","no2":"27","o3":"51","so2":"4","rank":null},{"time":"2018-01-25 09:00:00","aqi":"20","pm2_5":"6","pm10":"20","co":"0.5","no2":"28","o3":"50","so2":"4","rank":null},{"time":"2018-01-25 10:00:00","aqi":"21","pm2_5":"6","pm10":"21","co":"0.4","no2":"22","o3":"58","so2":"4","rank":null},{"time":"2018-01-25 11:00:00","aqi":"27","pm2_5":"9","pm10":"27","co":"0.4","no2":"17","o3":"63","so2":"5","rank":null},{"time":"2018-01-25 12:00:00","aqi":"25","pm2_5":"9","pm10":"25","co":"0.4","no2":"15","o3":"66","so2":"4","rank":null},{"time":"2018-01-25 13:00:00","aqi":"22","pm2_5":"9","pm10":"21","co":"0.4","no2":"14","o3":"68","so2":"4","rank":null},{"time":"2018-01-25 14:00:00","aqi":"23","pm2_5":"6","pm10":"18","co":"0.3","no2":"13","o3":"71","so2":"4","rank":null},{"time":"2018-01-25 15:00:00","aqi":"23","pm2_5":"7","pm10":"17","co":"0.3","no2":"13","o3":"71","so2":"4","rank":null},{"time":"2018-01-25 16:00:00","aqi":"23","pm2_5":"7","pm10":"19","co":"0.4","no2":"14","o3":"71","so2":"4","rank":null},{"time":"2018-01-25 17:00:00","aqi":"22","pm2_5":"8","pm10":"19","co":"0.3","no2":"17","o3":"68","so2":"4","rank":null},{"time":"2018-01-25 18:00:00","aqi":"20","pm2_5":"6","pm10":"20","co":"0.4","no2":"23","o3":"62","so2":"3","rank":null},{"time":"2018-01-25 19:00:00","aqi":"24","pm2_5":"7","pm10":"24","co":"0.4","no2":"29","o3":"54","so2":"4","rank":null},{"time":"2018-01-25 20:00:00","aqi":"23","pm2_5":"8","pm10":"23","co":"0.4","no2":"31","o3":"48","so2":"4","rank":null},{"time":"2018-01-25 21:00:00","aqi":"25","pm2_5":"11","pm10":"25","co":"0.5","no2":"39","o3":"39","so2":"4","rank":null},{"time":"2018-01-25 22:00:00","aqi":"26","pm2_5":"12","pm10":"26","co":"0.5","no2":"45","o3":"32","so2":"5","rank":null},{"time":"2018-01-25 23:00:00","aqi":"31","pm2_5":"13","pm10":"31","co":"0.6","no2":"50","o3":"25","so2":"5","rank":null}]}}}