ContentExtract/module/run_web_server.py

# -*- coding: utf-8 -*-
"""
Created on Fri Jun  1 18:03:03 2018

@author: DONG
"""
import sys
import os
import json
import re
sys.path.append(os.path.abspath(".."))
print(sys.path)
from flask import Flask, jsonify
from flask import abort
from flask import request
import logging
import time
import predictor
import uuid
import redis
import settings

app = Flask(__name__)
app.config['JSON_AS_ASCII'] = False

gunicorn_logger = logging.getLogger('gunicorn.error')
app.logger.handlers = gunicorn_logger.handlers
app.logger.setLevel(gunicorn_logger.level)

db = redis.StrictRedis(host=settings.REDIS_HOST,port=settings.REDIS_PORT,db=settings.REDIS_DB,password=settings.REDIS_PASS)


@app.route('/content_extract', methods=['POST'])
def text_predict():
    start_time = time.time()
    # 初始化待返回结果
    data = {"listpage_url": "","status_code":201}
    MAX_CONTENT = 150000
    # 确保请求符合要求
    if request.method == "POST":
        if (not request.json) or ('listpage_url' not in request.json):
            abort(400)
        else:
            try:
                k = str(uuid.uuid4())
                data["id"] = str(k)
                data["listpage_url"] = request.json["listpage_url"]
                
                if re.search("http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+",data["listpage_url"]) is None:
                    data["status_code"] = 400
                    abort(400)
                
                db.rpush(settings.CONTENT_QUEUE,json.dumps(data))
                
                while(True):
                    output = db.get(k)
                    if output is not None:
                        output = output.decode("utf-8")
                        json_output = json.loads(output)
                        data = json_output
                        data["listpage_url"] = request.json["listpage_url"]
                        # 从redis中移除数据并中断循环
                        db.delete(k)
                        break
                        
                    time.sleep(settings.SERVER_SLEEP)
                        
            except Exception as e:
                app.logger.info(msg="error:"+str(e))
                data["error_msg"] = str(e)
                        
                
        # 以json形式返回结果
        app.logger.info(" time from receive to send: "+str(time.time()-start_time))
        _resp = jsonify(data)
        app.logger.info(str(data["flag"])+str(data))
        return _resp, 201


if __name__ == '__main__':
    handler = logging.FileHandler('flask.log', encoding='UTF-8')
    app.logger.addHandler(handler)
    app.run(host='0.0.0.0', port=15015, threaded=True, debug=True)