腾讯招聘网数据爬取存入mongodb

#!/user/bin/env python3
# -*- coding: utf-8 -*-
import requests
from lxml import etree
from math import ceil
from mongodb_config import mongo_info

header = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 '
                  'Safari/537.36'}


# 获取岗位页数
def getJobPage(url):
    res = requests.get(url, headers=header)
    html = etree.HTML(res.text)
    total = html.xpath('//div[@class="left"]/span/text()')[0]
    job_page = ceil(int(total) / 10)
    return job_page


# 获取详情页职位描述
def getJobOrder(url):
    # url = 'https://hr.tencent.com/position_detail.php?id=49256&keywords=&tid=0&lid=0'
    res = requests.get(url, headers=header)
    html = etree.HTML(res.text)
    detail_info = html.xpath('//table[@class="tablelist textl"]')
    for item in detail_info:
        # 工作职责
        job_request = item.xpath('tr[3]//ul[@class="squareli"]/li/text()')
        # 工作要求
        job_order = item.xpath('tr[4]/td/ul[@class="squareli"]/li/text()')
        # print(job_request)
        # print(job_order)
        list_data = [job_request, job_order]
        return list_data


# 获取列表页岗位信息
def getJobInfo(url):
    res = requests.get(url, headers=header)
    html = etree.HTML(res.text)
    job_list = html.xpath('//tr[@class="even" or @class="odd"]')
    list_data = []
    href = 'https://hr.tencent.com/'
    for list_job in job_list:
        dict_item = {}
        # print(etree.tostring(list_job, encoding='utf-8').decode('utf-8'))
        detail_url = href + list_job.xpath('.//a/@href')[0]
        job_name = list_job.xpath('.//td[1]/a/text()')[0]
        job_type = list_job.xpath('.//td[2]/text()')[0]
        job_people = list_job.xpath('.//td[3]/text()')[0]
        job_addre = list_job.xpath('.//td[4]/text()')[0]
        job_time = list_job.xpath('.//td[5]/text()')[0]
        # 工作职责
        job_request = getJobOrder(detail_url)[0]
        # 工作要求
        job_order = getJobOrder(detail_url)[1]

        dict_item['detail_url'] = detail_url
        dict_item['job_name'] = job_name
        dict_item['job_type'] = job_type
        dict_item['job_people'] = job_people
        dict_item['job_addre'] = job_addre
        dict_item['job_time'] = job_time
        dict_item['job_request'] = job_request
        dict_item['job_order'] = job_order
        list_data.append(dict_item)
    mongo_info.update_tencent(list_data)
    print(list_data)


if __name__ == '__main__':
    mainurl = 'https://hr.tencent.com/position.php?&start=0#a'
    jobPage = getJobPage(mainurl)
    for page in range(jobPage):
        pageUrl = 'https://hr.tencent.com/position.php?&start=' + str(page * 10) + '#a'
        print("第" + str(page + 1) + "页")
        getJobInfo(pageUrl)
    # getJobOrder()

#!/user/bin/env python3
# -*- coding: utf-8 -*-
from pymongo import MongoClient


class Connect_mongo(object):
    def __init__(self):
        # 无密码认证使用该代码
        # self.client = MongoClient(host='127.0.0.1', port=27017)
        # self.client = MongoClient(host='192.168.1.191', port=27017)
        # 有密码认证使用该代码
        self.client = MongoClient(host='127.0.0.1', port=27017)
        # self.client = MongoClient(host='192.168.1.193', port=27017)
        # 数据库名loan
        self.database = self.client.loan
        self.tencent_database = self.client.tencent
        # 认证用户密码
        self.dbinfo = self.database.authenticate('xxx', 'xxxx')
        self.tencent_dbinfo = self.tencent_database.authenticate('xxx', 'xxx')

    # 无密码认证
    # 查询全部产品名
    def find_all_name(self):
        _database = self.client.loan
        _collection = _database.loan_datase_sums
        loan_name = _collection.find({}, {'_id': 0, 'loan_name': 1})
        return loan_name

    # 去重查询
    def find_distinct_name(self):
        _database = self.client.loan
        _collection = _database.loan_datase_sums
        loan_name = _collection.distinct('loan_name')
        return loan_name

    def update_data(self, document):
        _client = self.client
        _database = self.database
        self.dbinfo
        _collection = _database.loan_datase_sums
        for res in document:
            result = _collection.update_many({'loan_name': res['loan_name']}, {'$set': res}, upsert=True)
        return result

    def update_rong360(self, document):
        _client = self.client
        _database = self.database
        self.dbinfo
        _collection = _database.rong360
        for res in document:
            result = _collection.update_many({'loan_name': res['loan_name']}, {'$set': res}, upsert=True)
        return result

    def update_tencent(self, document):
        _client = self.client
        _database = self.tencent_database
        self.tencent_dbinfo
        _collection = _database.advertise_datase
        for res in document:
            result = _collection.update_many({'job_name': res['job_name']}, {'$set': res}, upsert=True)
        return result


mongo_info = Connect_mongo()