match_spider/qlm/source_qianlima.py

# coding: utf-8
import datetime
import json
import random
import time

import requests

from utils.databases import mongo_table, redis_client
from utils.log import logger
from utils.sessions_521 import http_session_521
from utils.tools import sha1

qlm = mongo_table('qlm', 'data_merge')
r = redis_client()
redis_key = "qianlima_2022"

headers = {
        "Accept": "*/*",
        "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
        "Cache-Control": "no-cache",
        "Connection": "keep-alive",
        "Content-Type": "application/json",
        "Origin": "http://search.vip.qianlima.com",
        "Pragma": "no-cache",
        "Referer": "http://search.vip.qianlima.com/index.html",
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.64 Safari/537.36",
        "X-Auth-Token": "6831ba66-f264-45b7-acaf-c0f7a85a12ce"
    }
cookies = {
        "BAIDU_SSP_lcr": "https://www.google.com/",
        "guest_id": "0124edcd-1edc-4434-ae60-5d44662dced0",
        "Hm_lvt_5dc1b78c0ab996bd6536c3a37f9ceda7": "1653874874",
        "Hm_lpvt_5dc1b78c0ab996bd6536c3a37f9ceda7": "1653874874",
        "seo_refUrl": "https%3A//www.google.com/",
        "seo_curUrl": "www.qianlima.com",
        "qlm_referrer": "https://www.google.com/",
        "qlm_rem_login": "1",
        "qlm_username": "17610673271",
        "qlm_password": "fmgj83E8oBfKRmKCBRuUR83pCB8pCCfE",
        "17610673271fmgj83E8oBfKRmKCBRuUR83pCB8pCCfE": "bc62b056-43d8-4f22-bfa6-606f59c2bbde",
        "source": "1",
        "useragent_hash": "1af3d6d4fbb7947d107b0170a309f510",
        "xAuthToken": "6831ba66-f264-45b7-acaf-c0f7a85a12ce",
        "login_time": "1653876714",
        "login_ip": "1.192.62.141",
        "__jsluid_h": "7d0d080a30094eb57be38e4c09dd4a3b",
        "userInfo": "{%22userId%22:10609848%2C%22username%22:%2217610673271%22%2C%22userIcon%22:%22%22%2C%22linkName%22:%22%E8%91%A3%E5%85%88%E7%94%9F%22%2C%22companyName%22:%22%E5%90%88%E8%82%A5%E6%8B%93%E6%99%AE%E7%BD%91%E7%BB%9C%E7%B3%BB%E7%BB%9F%E5%B7%A5%E7%A8%8B%E6%9C%89%E9%99%90%E8%B4%A3%E4%BB%BB%E5%85%AC%E5%8F%B8%22%2C%22areaId%22:%222703%22%2C%22areaName%22:%22%E5%85%A8%E5%9B%BD%22%2C%22roleId%22:1%2C%22roleName%22:%22%E7%AE%A1%E7%90%86%E5%91%98%22%2C%22sex%22:%22m%22%2C%22expireDate%22:%22%E6%97%A0%22%2C%22isExpired%22:null%2C%22maxChildCount%22:0%2C%22isUsedCount%22:0%2C%22userStatus%22:1%2C%22memberLevel%22:5%2C%22memberLevelName%22:%22%E5%85%8D%E8%B4%B9%E6%B3%A8%E5%86%8C%E4%BC%9A%E5%91%98%22%2C%22registerTime%22:%222022-05-30%22%2C%22isSuperSupplier%22:0%2C%22isNewUser%22:1%2C%22welcomeMsg%22:%22%E6%AC%A2%E8%BF%8E%E8%BF%9B%E5%85%A5%E5%8D%83%E9%87%8C%E9%A9%AC%E6%8B%9B%E6%A0%87%E7%BD%91%EF%BD%9E%22%2C%22customerServiceInfo%22:{%22id%22:42%2C%22customerServiceName%22:%22%E5%8D%83%E9%87%8C%E9%A9%AC%E5%AE%A2%E6%9C%8D%22%2C%22weChatIcon%22:%22http://img_al.qianlima.com/invoice/1588986761_8ebeade70a.jpg%22%2C%22customerServicePhone%22:%2217718573953%22%2C%22customerServiceQQ%22:%22%22%2C%22customerServiceEmail%22:%22qianlima_service@qianlima.com%22%2C%22deptType%22:0}%2C%22shouji%22:%2217610673271%22%2C%22email%22:%22%22%2C%22dwmc%22:%22%E5%90%88%E8%82%A5%E6%8B%93%E6%99%AE%E7%BD%91%E7%BB%9C%E7%B3%BB%E7%BB%9F%E5%B7%A5%E7%A8%8B%E6%9C%89%E9%99%90%E8%B4%A3%E4%BB%BB%E5%85%AC%E5%8F%B8%22%2C%22zhiwu%22:%22%E4%BA%A7%E5%93%81%E7%BB%8F%E7%90%86%22%2C%22types%22:1%2C%22isPayBefore%22:0%2C%22memberOpenTime%22:null%2C%22businessUserType%22:null%2C%22businessCompanyName%22:null%2C%22isBusinessUser%22:null}",
        "__jsl_clearance": "1653887986.259|0|v4obplHHBSE1zJOt5WFKuV0TdIM%3D"
}
session = requests.session()


def delay_by_day(days, fmt="%Y-%m-%d"):
    """按天延时"""
    _days = int(days)
    _current_now = datetime.datetime.now()
    return (_current_now + datetime.timedelta(days=_days)).strftime(fmt)


def crawl_request(url, data, retries=5):
    global session, cookies
    resp = None
    usages, usages_521 = 0, 1
    while usages < retries:
        request_params = {}
        request_params.setdefault('data', data)
        request_params.setdefault('headers', headers)
        request_params.setdefault('cookies', cookies)
        request_params.setdefault('timeout', 60)
        try:
            resp = session.post(url, **request_params)
            if resp.status_code == 521:
                while usages_521 < retries:
                    success, _, cookies = http_session_521(session, url, headers, cookies, data=data)
                    if success:
                        break
                    logger.info(f"反爬破解失败,次数:{usages_521}")
                    time.sleep(1)
                    usages_521 += 1
                usages += 1
            elif resp.status_code in [401, 403, 404]:
                logger.info(f"账号登录已失效或封停,异常状态码:{resp.status_code}")
                break
            else:
                break
        except requests.RequestException as e:
            logger.error(f"访问失败,失败原因:{e.__class__.__name__}")
            usages += 1
    # print(resp)
    return resp


def crawl_spider(area: str, page: int, **kwargs):
    curr_date = delay_by_day(0)
    begin_time = kwargs.pop('begin_time', curr_date)
    end_time = kwargs.pop('end_time', curr_date)
    max_page = kwargs.pop('max_page', 20)

    results = []
    request_status = 'failure'  # 资源请求结果, 成功=success 失败=failure 停止=stop 账号封停=disable

    data = {
        "keywords": "",
        "timeType": "4",  # 自定义时间参数
        "beginTime": begin_time,  # 格式: xxxx-xx-xxx
        "endTime": end_time,  # 格式: xxxx-xx-xxx
        "filtermode": 8,
        "searchMode": 0,
        "currentPage": page,  # 页码
        "numPerPage": max_page,  # 每页的条目数
        "sortType": "1",
        "allType": -1,
        "noticeSegmentTypeStr": "",
        "beginAmount": "",
        "endAmount": "",
        "purchasingUnitIdList": "",
        "threeClassifyTagStr": "",
        "fourLevelCategoryIdListStr": "",
        "threeLevelCategoryIdListStr": "",
        "levelId": "",
        "searchDataType": 0,
        "types": "-1",
        "showContent": 1,
        "hasTenderTransferProject": 1,
        "newAreas": area,  # 设置地区
        "hasChooseSortType": 1,
        "summaryType": 0
    }
    data = json.dumps(data)
    url = "http://search.vip.qianlima.com/rest/service/website/search/solr"
    response = crawl_request(url, data)
    if response is not None and response.status_code == 200:
        resp_json = response.json()
        if resp_json['code'] == 200:
            items = resp_json["data"]["data"]
            for item in items:
                tmid = sha1(str(item["contentid"]))
                if not r.hexists(redis_key, tmid):
                    r.hset(redis_key, tmid, '')

                    if "popTitle" in item:
                        item["title"] = item["popTitle"]
                    else:
                        item["title"] = item["showTitle"]

                    addr = str(item["areaName"]).split('-')
                    _area = addr[0] if len(addr) > 0 else ''
                    _city = addr[1] if len(addr) > 1 else ''
                    channel = (item['noticeSegmentTypeName'] or item['progName'])
                    res = {
                        'site': '千里马',
                        'channel': channel,
                        'area': _area,
                        'city': _city,
                        'title': item["title"],
                        'publishtime': item['updateTime'],
                        'competehref': item.get('url', '')
                    }
                    results.append(res)
            request_status = 'success'
            if len(items) < max_page:
                request_status = 'stop'
        else:
            '''
            {
                "code": 200520,
                "msg": "抱歉，您在单位时间内的搜索次数已达上限，请联系客服购买会员！咨询电话：400-688-2000",
                "data": null
            }
            '''
            logger.info(resp_json['msg'])
    elif response is not None and response.status_code in [401, 403, 404]:
        request_status = 'disable'

    if len(results) > 0:
        qlm.insert_many(results)

    if request_status in ['stop', 'success']:
        logger.info("第{}区第{}页成功上传{}条数据".format(area, len(results), page))
    return request_status


def start(**kwargs):
    pages = list(range(1, 1064))
    close_spider = False
    disable_page, max_disable_page = 0, 3
    while len(pages) > 0:
        if close_spider:
            break
        elif disable_page > max_disable_page:
            # 此处可以加入邮件或者企业微信通知，告知采集异常，人工排查问题
            break
        page = pages.pop(0)
        interval, max_interval = 2, 60
        logger.info(f"访问第{page}页数据")
        while True:
            success = crawl_spider("", page, **kwargs)
            if success == 'failure':
                interval = max_interval if interval > max_interval else interval
                time.sleep(random.randint(1, interval))
                interval += 3
                continue
            elif success == 'disable':
                logger.info(f"当前账号在第{page}页数据被禁止访问")
                disable_page += 1
                break
            elif success == 'stop':
                close_spider = True
            logger.info(f"第{page}页数据采集成功")
            break
    logger.info("采集任务结束")


if __name__ == '__main__':
    start(begin_time="2022-05-21", end_time="2022-05-28", max_page=1000)