# 創(chuàng)建主窗口
root = Tk()
root.title('職位查詢分析數(shù)據(jù)平臺 -- Dragon少年')
# 設(shè)置窗口大小
root.minsize(1380, 730)
root.resizable(False, False)
#得到屏幕寬度
sw = root.winfo_screenwidth()
#得到屏幕高度
sh = root.winfo_screenheight()
ww = 1380
wh = 730
x = (sw-ww) / 2
y = (sh-wh) / 2
root.geometry("%dx%d+%d+%d" %(ww,wh,x,y))
frame_left_top = Frame(width=1050, height=400)
frame_right_top = Frame(width=320, height=400)
# 定義列表區(qū)域
tree = ttk.Treeview(frame_left_top, show="headings", height=18,
                    columns=("n", "a", "b", "c", "d", "e", "f", "g", "h"))
vbar = ttk.Scrollbar(frame_left_top, orient=VERTICAL, command=tree.yview)
# 定義樹形結(jié)構(gòu)與滾動條
tree.configure(yscrollcommand=vbar.set)
# 表格的標題
tree.column("n", width=60, anchor="center")
tree.column("a", width=180, anchor="center")
tree.column("b", width=200, anchor="center")
tree.column("c", width=100, anchor="center")
tree.column("d", width=100, anchor="center")
tree.column("e", width=80, anchor="center")
tree.column("f", width=100, anchor="center")
tree.column("g", width=90, anchor="center")
tree.column("h", width=90, anchor="center")
tree.heading("n", text="序號")
tree.heading("a", text="崗位名稱")
tree.heading("b", text="公司名稱")
tree.heading("c", text="公司類型")
tree.heading("d", text="公司規(guī)模")
tree.heading("e", text="學歷")
tree.heading("f", text="工作經(jīng)驗")
tree.heading("g", text="最低工資（k）")
tree.heading("h", text="最高工資（k）")
tree.grid(row=0, column=0, sticky=NSEW)
vbar.grid(row=0, column=1, sticky=NS)
# 整體區(qū)域定位
frame_left_top.grid(row=0, column=0, padx=4, pady=5)
frame_right_top.grid(row=0, column=1, padx=2, pady=2)
frame_left_top.grid_propagate(0)
frame_right_top.grid_propagate(0)
type_str=StringVar()
#設(shè)置滾動窗口文本
habits = tk.LabelFrame(root, text="公司類型", padx=10, pady=4 )  # 水平，垂直方向上的邊距均為 10
habits.place(x=1035, y=170)
habits_Window = Label(habits, textvariable=type_str, width=30, height=10,  font=('楷體', 12))
habits_Window.grid()
size_str=StringVar()
#設(shè)置滾動窗口文本
company_size = tk.LabelFrame(root, text="公司規(guī)模", padx=10, pady=4 )  # 水平，垂直方向上的邊距均為 10
company_size.place(x=1035, y=370)
company_size_Window = Label(company_size, textvariable=size_str, width=30, height=8,  font=('楷體', 12))
company_size_Window.grid()
edu_str=StringVar()
#設(shè)置滾動窗口文本
company_edu = tk.LabelFrame(root, text="學歷要求", padx=10, pady=4 )  # 水平，垂直方向上的邊距均為 10
company_edu.place(x=1035, y=540)
company_edu_Window = Label(company_edu, textvariable=edu_str, width=30, height=8,  font=('楷體', 12))
company_edu_Window.grid()
# 打開文件
# right_top_button = Button(frame_right_top, text="打開文件", command=lambda :openFile(), font=('楷體', 12))
input_name = Label(frame_right_top, text='崗位關(guān)鍵字:', font=('楷體', 12)).place(x=0, y=10)
label = StringVar()
entry = Entry(frame_right_top, bg='#ffffff', width=20, textvariable=label, font=('楷體', 12)).place(x=120, y=10)
input_num = Label(frame_right_top, text='數(shù)據(jù)條數(shù):', font=('楷體', 12)).place(x=0, y=50)
label_num = StringVar()
entry_num = Entry(frame_right_top, bg='#ffffff', width=15, textvariable=label_num, font=('楷體', 12)).place(x=80, y=50)
btn_search = Button(frame_right_top, text="查詢輸出", command=lambda :openFile(label, label_num), font=('楷體', 12)).place(x=210, y=50)
right_pic_button = Button(frame_right_top, text="工作經(jīng)驗對應(yīng)薪資圖", command=lambda: show_plot(), font=('楷體', 12)).place(x=0, y=90)
right_hist_button = Button(frame_right_top, text="工資分布圖", command=lambda: show_hist(), font=('楷體', 12)).place(x=180, y=90)
right_data_button = Button(frame_right_top, text="數(shù)據(jù)分析", command=lambda: show_data(), font=('楷體', 12)).place(x=0, y=130)

# 獲取一個列表頁
def geturl(url):
    headers = {
        'User-Agent': 'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 '
                      '(KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'
    }
    # 使用通用爬蟲對url進行一頁進行爬取
    page_text = requests.get(url=url, headers=headers).text       # 每一頁源碼用text
    # print(page_text)
    return page_text

# 獲取列表頁的所有崗位信息
def get_data(page_text):
    # 正則表達式提取崗位信息
    job_href = '"job_href":"(.*?)"'              # 崗位鏈接
    job_name = '"job_name":"(.*?)"'              # 崗位名稱
    com_href = '"company_href":"(.*?)"'          # 公司鏈接
    com_name = '"company_name":"(.*?)"'          # 公司名稱
    salary = '"providesalary_text":"(.*?)"'     # 薪資水平
    company_type = '"companytype_text":"(.*?)"'  # 公司類型
    attribute = '"attribute_text":\[(.*?)\]'     # 招聘條件
    work_area = '"workarea_text":"(.*?)"'        # 工作地點
    company_size = '"companysize_text":"(.*?)"'  # 公司規(guī)模
    company_ind = '"companyind_text":"(.*?)"'    # 主要業(yè)務(wù)
    job_welf = '"jobwelf":"(.*?)"'               # 福利待遇
    # 第一個參數(shù)是規(guī)則，第二個參數(shù)是被檢索內(nèi)容，第三個參數(shù)re.S是單行匹配
    jobName_list = re.findall(job_name, page_text, re.S)
    comName_list = re.findall(com_name, page_text, re.S)
    salary_list = re.findall(salary, page_text, re.S)
    companytype_list = re.findall(company_type, page_text, re.S)
    attribute_list = re.findall(attribute, page_text, re.S)
    workarea_list = re.findall(work_area, page_text, re.S)
    companysize_list = re.findall(company_size, page_text, re.S)
    companyind_list = re.findall(company_ind, page_text, re.S)
    jobwelf_list = re.findall(job_welf, page_text, re.S)
    all_list = [jobName_list, comName_list, salary_list,
                companytype_list, attribute_list, workarea_list, companysize_list,
                companyind_list, jobwelf_list]
    return all_list

# 主函數(shù)
def main(kw, num):
    # 關(guān)鍵字二次轉(zhuǎn)譯
    # kw = input("請輸入你要搜索的崗位關(guān)鍵字：")
    keyword = parse.quote(parse.quote(kw))
    page_num = 0
    col = ["崗位名稱", "公司名稱", "薪資水平", "公司類型", "招聘條件", "工作地點", '公司規(guī)模', '主要業(yè)務(wù)', '福利待遇']
    csv_file = open("51job.csv", "w+", encoding='utf-8', newline='')
    try:
        writer = csv.writer(csv_file)
        writer.writerow(col)
        for i1 in range(0, num):  # 爬取前3頁數(shù)據(jù)
            page_num += 1
            url = "https://search.51job.com/list/080000,000000,0000,00,9,99," + keyword + ",2," + str(
                page_num) + ".html"
            page_text = geturl(url)
            all_list = get_data(page_text)
            if len(all_list[0]) == 0:
                print('沒有搜索到職位信息')
                break
            else:
                print('正在爬取第%d頁' % page_num)
                save_data(all_list, writer, search_num=len(all_list[0]))
    finally:
        csv_file.close()

job = pd.read_csv("51job.csv", encoding='utf-8')
df = pd.DataFrame(job)
dict_city = {'杭州': 0, '湖州': 0, '紹興': 0, '寧波': 0, '嘉興': 0, '麗水': 0, '臺州': 0, '溫州': 0, '金華': 0, '衢州': 0, '舟山': 0}
city = df.loc[:, "工作地點"]
print(city.shape[0])
for i in range(city.shape[0]):
    # print(city[i])
    for k, v in dict_city.items():
        # print(k, v)
        if k in city[i]:
            dict_city[k] = dict_city[k] + 1
            df.loc[i, "城市"] = k
            break
# print(list(dict_city.keys()))
# print(list(dict_city.values()))
city_df = df["城市"]
if np.any(pd.notnull(df["城市"])):
    df["城市"].fillna("其他", inplace=True)
# print(df["城市"].value_counts())

def get_salary(salary):
    if '-' in salary:  # 針對1-2萬/月或者10-20萬/年的情況，包含-
        low_salary = re.findall(re.compile('(\d*\.?\d+)'), salary)[0]
        high_salary = re.findall(re.compile('(\d?\.?\d+)'), salary)[1]
        if u'萬' in salary and u'年' in salary:  # 單位統(tǒng)一成千/月的形式
            low_salary = round(float(low_salary) / 12 * 10, 1)
            high_salary = round(float(high_salary) / 12 * 10, 1)
        elif u'萬' in salary and u'月' in salary:
            low_salary = float(low_salary) * 10
            high_salary = float(high_salary) * 10
    else:  # 針對20萬以上/年和100元/天這種情況，不包含-，取最低工資，沒有最高工資
        low_salary = re.findall(re.compile('(\d*\.?\d+)'), salary)[0]
        if u'萬' in salary and u'年' in salary:  # 單位統(tǒng)一成千/月的形式
            low_salary = round(float(low_salary) / 12 * 10, 1)
        elif u'萬' in salary and u'月' in salary:
            low_salary = float(low_salary) * 10
        elif u'元' in salary and u'天' in salary:
            low_salary = round(float(low_salary) / 1000 * 21, 1)   # 每月工作日21天
        elif u'元' in salary and u'小時' in salary:
            low_salary = round(float(low_salary) / 1000 * 8 * 21, 1)   # 每天8小時，每月工作日21天
        high_salary = low_salary
    return low_salary, high_salary

job = pd.read_csv("51job_pre.csv", encoding='utf-8')
job_df = job.drop("福利待遇", axis=1)
job_df = job_df.dropna(axis=0, how="any")
for index, row in job_df.iterrows():
    salary = row["薪資水平"]
    if salary:  # 如果待遇這欄不為空，計算最低最高待遇
        getsalary = get_salary(salary)
        low_salary = getsalary[0]
        high_salary = getsalary[1]
    else:
        low_salary = high_salary = "0"
    job_df.loc[index, "最低工資（k）"] = low_salary
    job_df.loc[index, "最高工資（k）"] = high_salary
    job_df.loc[index, "平均工資（k）"] = round((float(low_salary) + float(high_salary)) / 2, 1)
job_df.to_csv("./51job_pre2.csv", index=False)

job_df.to_csv("./51job_pre2.csv", index=False)
job_df = pd.read_csv("51job_pre2.csv", encoding='utf-8')
job_df["學歷"] = job_df["招聘條件"].apply(lambda x: re.findall("本科|大專|高中|中專|碩士|博士|初中及以下", x))
job_df["工作經(jīng)驗"] = job_df["招聘條件"].apply(lambda x: re.findall(r',".*經(jīng)驗"|,"在校生/應(yīng)屆生"', x))
job_df["學歷"] = job_df["學歷"].apply(func)
job_df["工作經(jīng)驗"] = job_df["工作經(jīng)驗"].apply(func2)
# 薪資水平,公司類型,招聘條件,工作地點,公司規(guī)模,主要業(yè)務(wù),城市,最低工資（k）,最高工資（k）,平均工資（k）
job_df = job_df.drop(["薪資水平", "招聘條件", "工作地點", "主要業(yè)務(wù)", "城市"], axis=1)
job_df = job_df.dropna(axis=0, how="any")
job_df.to_csv("./51job_analysis.csv", index=False)

def read_csv_define(csv_path):
    x = tree.get_children()
    for item in x:
        tree.delete(item)
    global job_df
    job_df = pd.read_csv(csv_path, encoding='utf-8')
    # print(job_df.shape[0])
    for i in range(job_df.shape[0]):
        tree.insert("", "end",
                    values=(i+1, job_df.loc[job_df.index[i], "崗位名稱"], job_df.loc[job_df.index[i], "公司名稱"],\
                            job_df.loc[job_df.index[i], "公司類型"], job_df.loc[job_df.index[i], "公司規(guī)模"], \
                             job_df.loc[job_df.index[i], "學歷"],job_df.loc[job_df.index[i], "工作經(jīng)驗"], \
                            job_df.loc[job_df.index[i], "最低工資（k）"], job_df.loc[job_df.index[i], "最高工資（k）"]))

def openFile(label, label_num):
    sname = label.get()
    num_str = label_num.get()
    num = int(num_str)
    rep.main(sname, int(num/50))
    pre.main()
    Filepath = "./51job_analysis.csv"
    # 打開文件選擇對話框
    # Filepath = filedialog.askopenfilename(filetypes=[('表格', '*.xls;*.csv')]) #過濾文件后綴類型
    # print(os.path.split(Filepath))
    (filepath, tempfilename) = os.path.split(Filepath)  # 右側(cè)的值是元組類型
    try:
        # Filepath 當路徑存在的時候繼續(xù)
        if Filepath:
            # 傳輸excel表格的路徑
            # 調(diào)用讀取數(shù)據(jù)的函數(shù)，趁著用戶正在查看查詢條件的時候 將數(shù)據(jù)注入到全局變量中 減少查詢等待
            # 由于兩種表格文件的讀取模塊不同，需要做處理判斷屬于哪種文件類型，故采用下邊的方式進行判斷
            # 從文件名中分離出后綴
            (filename, extension) = os.path.splitext(tempfilename)
            if extension == '.xls' or extension == '.XLS':
                read_xls(Filepath)
            elif extension == '.csv':
                read_csv_define(Filepath)
        else:
            print('未選擇任何文件!')
            # exit_program()
    except Exception as e:
        global job_df
        job_df = pd.DataFrame()
        tkinter.messagebox.showwarning('警告', '文件讀取異常，請檢查！')
        print("ex:", e)
    finally:
        size_str.set("")
        type_str.set("")
        edu_str.set("")
        canvas_spice.get_tk_widget().destroy()
        canvas_spice_hist.get_tk_widget().destroy()

def show_plot():
    global canvas_spice
    canvas_spice.get_tk_widget().destroy()
    # 圖像及畫布
    fig, ax = plt.subplots(figsize=(5, 3.2), dpi=100)  # 圖像比例
    canvas_spice = FigureCanvasTkAgg(fig, root)
    canvas_spice.get_tk_widget().place(x=5, y=400)  # 放置位置
    work_experience = round(job_df.groupby(by='工作經(jīng)驗')['平均工資（k）'].mean(), 2)
    experience_list = ["無需經(jīng)驗", "1年經(jīng)驗", "2年經(jīng)驗", "3-4年經(jīng)驗", "5-7年經(jīng)驗"]
    experience_val = [work_experience[i] for i in experience_list]
    x = range(len(experience_list))
    y = experience_val
    plt.plot(x, y)
    plt.xticks(x, experience_list, fontsize=6)
    plt.grid(True, linestyle="--", alpha=0.5)
    plt.xlabel("工作經(jīng)驗", fontsize=8)
    plt.ylabel("平均工資（k）", fontsize=8)
    plt.title("工作經(jīng)驗對應(yīng)薪資折線圖", fontsize=8)
    canvas_spice.draw()
    canvas_spice.get_tk_widget().bind("<Double-Button-1>", xFunc1)

def show_hist():
    global canvas_spice_hist
    canvas_spice_hist.get_tk_widget().destroy()
    # 圖像及畫布
    fig_hist, ax_hist = plt.subplots(figsize=(5, 3.2), dpi=100)  # 圖像比例
    canvas_spice_hist = FigureCanvasTkAgg(fig_hist, root)
    canvas_spice_hist.get_tk_widget().place(x=520, y=400)  # 放置位置
    plt.hist(job_df["平均工資（k）"].values, bins=10)
    # 求出最小值
    max_ = job_df["平均工資（k）"].max()
    min_ = job_df["平均工資（k）"].min()
    # 修改刻度
    plt.xticks(np.linspace(min_, max_, num=11),fontsize=7)
    # 添加網(wǎng)格
    plt.grid()
    plt.xlabel("平均工資（k）", fontsize=8)
    plt.ylabel("崗位數(shù)量", fontsize=8)
    plt.title("工資分布直方圖", fontsize=8)
    canvas_spice_hist.draw()
    canvas_spice_hist.get_tk_widget().bind("<Double-Button-1>", xFunc2)

def show_data():
    company = job_df.loc[:, "公司類型"].value_counts()
    type_name = list(company.index)
    x = range(len(type_name))
    content = ""
    for item in x:
        content += type_name[item] + '----' + str(company[item]) + '\n'
    type_str.set(content)
    company = job_df.loc[:, "公司規(guī)模"].value_counts()
    company_scale = company.index.to_list()
    z = range(len(company_scale))
    size_content = ""
    for item in z:
        size_content += company_scale[item] + '----' + str(company[item]) + '\n'
    size_str.set(size_content)
    education = job_df.loc[:, "學歷"].value_counts()
    education_scale = education.index.to_list()
    y = range(len(education_scale))
    edu_content = ""
    for item in y:
        edu_content += education_scale[item] + '----' + str(education[item]) + '\n'
    edu_str.set(edu_content)

def handlerAdaptor(fun, **kwds):
    return lambda event, fun= fun, kwds= kwds:fun(event, **kwds)

def xFunc2(event):
    top = Toplevel()
    top.title('圖像導出')
    top.minsize(700, 450)
    top.resizable(False, False)
    # 得到屏幕寬度
    sw = root.winfo_screenwidth()
    # 得到屏幕高度
    sh = root.winfo_screenheight()
    ww = 700
    wh = 450
    x = (sw - ww) / 2
    y = (sh - wh) / 2
    top.geometry("%dx%d+%d+%d" % (ww, wh, x, y))
    top.transient(root)
    top.grab_set()
    # 圖像及畫布
    fig, ax = plt.subplots(figsize=(7, 4.5), dpi=100)  # 圖像比例
    canvas_spice = FigureCanvasTkAgg(fig, top)
    canvas_spice.get_tk_widget().place(x=1, y=1)  # 放置位置
    plt.hist(job_df["平均工資（k）"].values, bins=10)
    # 求出最小值
    max_ = job_df["平均工資（k）"].max()
    min_ = job_df["平均工資（k）"].min()
    # 修改刻度
    plt.xticks(np.linspace(min_, max_, num=11), fontsize=10)
    # 添加網(wǎng)格
    plt.grid()
    plt.xlabel("平均工資（k）", fontsize=12)
    plt.ylabel("崗位數(shù)量", fontsize=12)
    plt.title("工資分布直方圖", fontsize=15)
    plt.savefig("hist.png")
    canvas_spice.draw()
    canvas_spice.get_tk_widget().pack()
    img_pl = Image.open("hist.png").copy()
    os.remove("hist.png")
    canvas_spice.get_tk_widget().bind("<Button-3>", handlerAdaptor(saveimg, img=img_pl))

def saveimg(event, img):
    Filepath = filedialog.asksaveasfilename(filetypes=[('圖像', '*.png;')])
    if Filepath:
        if not Filepath.endswith(('.png')):
            Filepath += '.png'
        # 保存獲得的圖像
        img.save(Filepath, 'png')
        tkinter.messagebox.showinfo("提示", "保存成功！")
        HWND = win32gui.GetFocus()  # 獲取當前窗口句柄
        win32gui.PostMessage(HWND, win32con.WM_CLOSE, 0, 0)