秋招季，用Python分析深圳程序员工资有多高？

/* 1 */
{
    "_id" : ObjectId("5b8b89328ffaed60a308bacd"),
    "education" : "本科",# 学习要求
    "companySize" : "2000人以上",# 公司人数规模
    "name" : "python开发工程师",# 职位名称
    "welfare" : "“朝九晚五,公司平台大,发展机遇多,六险一金”",# 公司福利
    "salaryMid" : 12.5,# 工资上限与工资下限的平均数
    "companyType" : "移动互联网",# 公司类型
    "salaryMin" : "10",# 工资下限
    "salaryMax" : "15",# 工资上限
    "experience" : "经验3-5年",# 工作年限
    "companyLevel" : "不需要融资",# 公司级别
    "company" : "XXX技术有限公司"# 公司名称
}

# 获取网页源码数据
# language => 编程语言
# city => 城市
# collectionType => 值：True/False  True => 数据库表以编程语言命名   False => 以城市命名
def main(self, language, city, collectionType):
    print(" 当前爬取的语言为 => " + language + "  当前爬取的城市为 => " + city)
    url = self.getUrl(language, city)
    browser = webdriver.Chrome()
    browser.get(url)
    browser.implicitly_wait(10)
    for i in range(30):
        selector = etree.HTML(browser.page_source)  # 获取源码
        soup = BeautifulSoup(browser.page_source, "html.parser")
        span = soup.find("div", attrs={"class": "pager_container"}).find("span", attrs={"action": "next"})
        print(
            span)  # <span action="next" class="pager_next pager_next_disabled" hidefocus="hidefocus">下一页<strong class="pager_lgthen pager_lgthen_dis"></strong></span>
        classArr = span['class']
        print(classArr)  # 输出内容为 -> ['pager_next', 'pager_next_disabled']
        attr = list(classArr)[0]
        attr2 = list(classArr)[1]
        if attr2 == "pager_next_disabled":#分析发现 class 属性为  ['pager_next', 'pager_next_disabled'] 时，【下一页】按钮不可点击
            print("已经爬到最后一页，爬虫结束")
            break
        else:
            print("还有下一页，爬虫继续")
            browser.find_element_by_xpath('//*[@id="order"]/li/div[4]/div[2]').click()  # 点击【下一页】按钮
        time.sleep(5)
        print('第{}页抓取完毕'.format(i + 1))
        self.getItemData(selector, language, city, collectionType)# 解析 item 数据，并存进数据库
    browser.close()

# 获取各语言样本数量
def getLanguageNum(self):
    analycisList = []
    for index, language in enumerate(self.getLanguage()):
        collection = self.zfdb["z_" + language]
        totalNum = collection.aggregate([{'$group': {'_id': '', 'total_num': {'$sum': 1}}}])
        totalNum2 = list(totalNum)[0]["total_num"]
        analycisList.append(totalNum2)
    return (self.getLanguage(), analycisList)

# 获取各语言的平均工资
def getLanguageAvgSalary(self):
    analycisList = []
    for index, language in enumerate(self.getLanguage()):
        collection = self.zfdb["z_" + language]
        totalSalary = collection.aggregate([{'$group': {'_id': '', 'total_salary': {'$sum': '$salaryMid'}}}])
        totalNum = collection.aggregate([{'$group': {'_id': '', 'total_num': {'$sum': 1}}}])
        totalNum2 = list(totalNum)[0]["total_num"]
        totalSalary2 = list(totalSalary)[0]["total_salary"]
        analycisList.append(round(totalSalary2 / totalNum2, 2))
    return (self.getLanguage(), analycisList)

# 获取一门语言的学历要求（用于 pyecharts 的词云）
def getEducation(self, language):
    results = self.zfdb["z_" + language].aggregate([{'$group': {'_id': '$education', 'weight': {'$sum': 1}}}])
    educationList = []
    weightList = []
    for result in results:
        educationList.append(result["_id"])
        weightList.append(result["weight"])
    # print(list(result))
    return (educationList, weightList)

# 获取一门语言的工作年限要求（用于 pyecharts 的词云）
def getExperience(self, language):
    results = self.zfdb["z_" + language].aggregate([{'$group': {'_id': '$experience', 'weight': {'$sum': 1}}}])
    totalAvgPriceDirList = []
    for result in results:
        totalAvgPriceDirList.append(
            {"value": result["weight"], "name": result["_id"] + "  " + str(result["weight"])})
    return totalAvgPriceDirList

# 获取 welfare 数据，用于构建福利词云
def getWelfare(self):
    content = ''
    queryArgs = {}
    projectionFields = {'_id': False, 'welfare': True}  # 用字典指定
    for language in self.getLanguage():

        collection = self.zfdb["z_" + language]
        searchRes = collection.find(queryArgs, projection=projectionFields).limit(1000)
        for result in searchRes:
            print(result["welfare"])
            content += result["welfare"]
    return content

# 获取公司级别排行（用于条形图）
def getAllCompanyLevel(self):
    levelList = []
    weightList = []
    newWeightList = []
    attrList = ["A轮", "B轮", "C轮", "D轮及以上", "不需要融资", "上市公司"]
    for language in self.getLanguage():
        collection = self.zfdb["z_" + language]
        # searchRes = collection.find(queryArgs, projection=projectionFields).limit(1000)
        results = collection.aggregate([{'$group': {'_id': '$companyLevel', 'weight': {'$sum': 1}}}])
        for result in results:
            levelList.append(result["_id"])
            weightList.append(result["weight"])
    for index, attr in enumerate(attrList):
        newWeight = 0
        for index2, level in enumerate(levelList):
            if attr == level:
                newWeight += weightList[index2]
        newWeightList.append(newWeight)
    return (attrList, newWeightList)