conf_platform/server/conf_task.py

import os
import sys
import time

import requests
from flask import Flask, request
from flask import jsonify

sys.path.append(os.path.abspath(os.path.join(os.getcwd(), "..")))
from common.db.mysql_help import MysqlHelper
from user_spider.user_info import *

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


# 只接受get方法访问
@app.route("/v1/crawler/source/getall", methods=["GET"])
def getSource():
    try:
        # 获取传入的params参数
        get_data = request.args.to_dict()
        fields = get_data.get('fields')
        # # 对参数进行操作
        sql = 'select source, task_type, spider_name, machine, source_desc, task_type_desc, spider_name_desc from crawler_source'

        result = MysqlHelper.get_values(sql)
        if not result:
            return jsonify({'code': '200', 'result': [], 'message': '没有更多数据'})
        source_list = list()

        # [
        #     {
        #         'description': task_type_desc,
        #         'type': [
        #             {
        #                 'spider_name': spider_name,
        #                 'description': spider_name_desc
        #             }
        #         ],
        for source, task_type, spider_name, machine, source_desc, task_type_desc, spider_name_desc in result:
            source_dict = {
                'task_type': [
                    {
                        'type': task_type,
                        'description': task_type_desc,
                        'spider': {
                            'spider_name': spider_name,
                            'description': spider_name_desc
                        }
                    }
                ],
                'description': source_desc,
                'source': source,
                'machine': machine
            }
            source_list.append(source_dict)
    except Exception as e:
        return jsonify({'code': '400', 'message': '获取数据源信息失败'})

    return jsonify({'code': '200', 'result': source_list})


@app.route("/v1/crawler/task/insert", methods=["POST"])
def insertTask():
    try:
        data = request.form
        outer_info = data.get(('spider_link'))
        source = data.get('source')
        exist_outer_info = list()
        for link in outer_info:
            s_sql = f"""select spider_link from crawler_task where source={source}"""
            result = MysqlHelper.get_values(s_sql)
            if link in eval(result[0]):
                exist_outer_info.append(link)
        if exist_outer_info:
            return jsonify({'code': 200, 'message': '名单重复', 'repeat_list': exist_outer_info})
        # 获取到一个以键且为逗号分隔的字符串，返回一个字符串
        keys = ','.join(data.keys())
        values = ','.join(['%s'] * len(data))
        sql = 'insert into {table}({keys}) VALUES({values})'.format(table='crawler_task', keys=keys, values=values)
        MysqlHelper.insert_values(sql, tuple(data.values()))
    except Exception as e:
        return jsonify({'code': 400, 'message': '任务写入失败'})

    return jsonify({'code': 200, 'message': 'task create success'})


@app.route("/v1/crawler/task/gettask", methods=["GET"])
def getAllTask():
    try:
        get_data = request.args.to_dict()
        page = int(get_data.get('page', 1))
        offset = int(get_data.get('offset', 10))
        start_count = (page * offset) - offset
        end_count = page * offset
        sql = f"""select task_id, task_name from crawler_task limit {start_count}, {end_count}"""
        result = MysqlHelper.get_values(sql)
        if not result:
            return jsonify({'code': '200', 'result': [], 'message': 'no data'})
        source_list = list()
        for task_id, task_name in result:
            data = dict(
                task_id=task_id,
                task_name=task_name,
            )
            source_list.append(data)
    except Exception as e:
        return jsonify({"code": "400", 'message': "任务列表获取失败"})

    return jsonify({'code': '200', 'result': source_list})


@app.route("/v1/crawler/task/getone", methods=["GET"])
def getOneTask():
    try:
        get_data = request.args.to_dict()
        task_id = get_data['task_id']
        sql = f'select task_id, spider_link from crawler_task where task_id={task_id}'
        result = MysqlHelper.get_values(sql)
        if not result:
            return jsonify({'code': '200', 'result': [], 'message': 'no data'})
        for task_id, spider_link in result:
            data = dict(
                task_id=task_id,
                spider_link=spider_link,
            )
    except Exception as e:
        return jsonify({'code': '400', "message": "获取任务信息失败"})

    return jsonify({'code': '200', 'result': data})


@app.route("/v1/crawler/task/update", methods=["POST"])
def updateTask():
    try:
        task_id = request.form.get('task_id')
        spider_link = request.form.get('spider_link')
        print(spider_link, task_id)

        sql = f"""UPDATE crawler_task SET spider_link='{spider_link}' where task_id = {task_id}"""
        print(sql)
        result = MysqlHelper.update_values(sql)
        if result:
            return jsonify({'code': 200, 'message': 'task update success'})
        else:
            return jsonify({'code': 400, 'message': 'task update faild'})
    except Exception as e:

        return jsonify({'code': 400, 'message': '任务更新失败'})


def get_user_info(source):
    source_spider = {
        'xigua': xigua_user_info
    }
    return source_spider.get(source)


@app.route("/v1/crawler/author/create", methods=["POST"])
def createUser():
    get_media_url = 'http://videotest-internal.yishihui.com/longvideoapi/user/virtual/crawler/registerVirtualUser'
    spider_link = request.form.get('spider_link')
    source = request.form.get('source')
    task_type = request.form.get('task_type')
    applets_status = request.form.get('applets_status')
    app_status = request.form.get('app_status')
    user_tag = request.form.get('user_tag')
    user_content_tag = request.form.get('user_content_tag')
    success_list = list()
    fail_list = list()
    for author_url in eval(spider_link):
        try:
            post_data = {
                # 'count': 1,     # （必须）账号个数：传1
                # 'accountType': 4,   # （必须）账号类型 ：传 4 app虚拟账号
                'pwd': '',  # 密码 默认 12346
                'nickName': '',  # 昵称  默认 vuser......
                'avatarUrl': '',
                # 头像Url  默认 http://weapppiccdn.yishihui.com/resources/images/pic_normal.png
                'tagName': user_tag,  # 多条数据用英文逗号分割
            }
            response = requests.post(url=get_media_url, params=post_data)
            media_id = response.json()['data']
            f_sql = f"""select spider_link from crawler_author_map where spider_link="{author_url}" """
            result = MysqlHelper.get_values(f_sql)
            if result:
                success_list.append(author_url)
                continue
            else:
                data = dict(
                    spider_link=author_url,
                    media_id=media_id,
                    source=source,
                    task_type=task_type,
                    applets_status=applets_status,
                    app_status=app_status,
                    user_tag=user_tag,
                    user_content_tag=user_content_tag,
                    insert_time=int(time.time()),
                    update_time=int(time.time())
                )
                keys = ','.join(data.keys())
                values = ','.join(['%s'] * len(data))
                table = 'crawler_author_map'
                sql = f"""insert into {table}({keys}) VALUES({values})"""
                result = MysqlHelper.insert_values(sql, tuple(data.values()))
                if not result:
                    fail_list.append(author_url)
                else:
                    success_list.append(author_url)
        except Exception as e:
            fail_list.append(author_url)
            continue
    return jsonify({'code': 200, 'result': {'success': success_list, 'fail': fail_list}})


if __name__ == "__main__":
    app.run(debug=True, port=5050)