不废话，直接上代码
#-*-coding:GBK -*-
import urllib.request
import requests
import re
import webbrowser
import ctypes #隐藏控制台库
import threading #多线程
import random
from tkinter import *
import tkinter as tk
import sys
from urllib.parse import urlencode
import pandas as pd #制表模块
from urllib.parse import urlparse
my_headers = [
"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:30.0) Gecko/20100101 Firefox/30.0",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 Safari/537.75.14",
"Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Win64; x64; Trident/6.0)",
'Mozilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11',
'Opera/9.25 (Windows NT 5.1; U; en)',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)',
'Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Kubuntu)',
'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.12) Gecko/20070731 Ubuntu/dapper-security Firefox/1.5.0.12',
'Lynx/2.8.5rel.1 libwww-FM/2.14 SSL-MM/1.4.1 GNUTLS/1.2.9',
"Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.7 (KHTML, like Gecko) Ubuntu/11.04 Chromium/16.0.912.77 Chrome/16.0.912.77 Safari/535.7",
"Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:10.0) Gecko/20100101 Firefox/10.0 "
]
headers = {'User-Agent':random.choice(my_headers)}
def get_page(url):#封装下载页面方法
response = requests.get(url,headers=headers)
if response.status_code == 200:
return response.content.decode("utf-8")#应对乱码
else:
return '爬取失败！'
def parse_html(html_content):
pattern = re.compile('.*?fname fl.*?>(.*?)\D(\d+)\D</a>.*?单位净值.*?>(.*?)</span>.*?<span.*?>(.*?)</span>.*?基金类型：(.*?)</li>.*?管 理 人：.*?>(.*?)</a>.*?规 模</a>：((---)|(.*?)亿元).*?基金经理：.*?>(.*?)</a>', re.S)#(.*?fname fl.*?>(.*?)\D(\d+)\D</a>).*?ping.*?>(.*?)</span>.*?基金类型：(.*?)</li>.*?管 理 人：.*?>(.*?)</a>.*?规 模</a>：(.*?)亿元.*?基金经理：.*?>(.*?)</a>.*?手 续 费</a>：(.*?)<', re.S)
result1 = re.findall(pattern, html_content)
return result1
def parse_html_list(html_content_list):
pattern = re.compile('.*?{.*?\[(.*?)].*?',re.S)
result_list = re.findall(pattern, html_content_list)
return result_list
def parse_html_list_up(html_content_list_up):
pattern = re.compile('\"(.*?)\"',re.S)
result_list_up = re.findall(pattern, html_content_list_up)
return result_list_up
def parse_html1(html):
pattern = re.compile('.*?allPages.*?(\d+)', re.S)
result2 = re.findall(pattern, html)
return result2
def thread_it(func, *args):
'''将函数打包进线程'''
# 创建
t = threading.Thread(target=func, args=args)
# 守护 !!!
t.setDaemon(True)
# 启动
t.start()
# 阻塞--卡死界面！
# t.join()
def hideConsole(): #隐藏控制台
whnd = ctypes.windll.kernel32.GetConsoleWindow()
if whnd != 0:
ctypes.windll.user32.ShowWindow(whnd, 0)
def main_windows():
# 第1步，实例化object，建立窗口window
window = tk.Tk()
# 第2步，给窗口的可视化起名字
window.title('天天基金数据下载工具')
window.resizable(0, 0)
# 第3步，设定窗口的大小(长 * 宽)
screenwidth = window.winfo_screenwidth()
screenheight = window.winfo_screenheight()
dialog_width = 800
dialog_height = 480
window.geometry("%dx%d+%d+%d" % (
dialog_width, dialog_height, (screenwidth - dialog_width) / 2, (screenheight - dialog_height) / 2)) # 这里的乘是小x
def test(content, reason, name):
return True
class myStdout(): # 重定向类
def __init__(self):
# 将其备份
self.stdoutbak = sys.stdout
self.stderrbak = sys.stderr
# 重定向
sys.stdout = self
sys.stderr = self
def write(self, info):
# info信息即标准输出sys.stdout和sys.stderr接收到的输出信息
t.insert('end', info) # 在多行文本控件最后一行插入print信息
t.update() # 更新显示的文本，不加这句插入的信息无法显示
t.see(tk.END) # 始终显示最后一行，不加这句，当文本溢出控件最后一行时，不会自动显示最后一行
def restoreStd(self):
# 恢复标准输出
sys.stdout = self.stdoutbak
sys.stderr = self.stderrbak
mystd = myStdout()
test_cmd = window.register(test)
v_1 = StringVar()
v_1.set('http://fund.eastmoney.com/daogou/#dt4;ft;rs;sd;ed;pr;cp;rt;tp;rk;se;nx;sc3y;stdesc;pi1;pn20;zfdiy;shlist')
v_2 = StringVar()
v_2.set('基金数据表格')
#test_cmd = window.register(test)
tk.Label(window, text='输入天天基金数据网址', font=('宋体', 12)).place(x=260, y=28)
tk.Label(window, text='表格名称', font=('宋体', 12)).place(x=180, y=80)
e1 = tk.Entry(window,
width=100,
textvariable=v_1,
validate='all', # 发生任何变动的时候，就会调用validatecommand
validatecommand=(test_cmd, '%P', '%v', '%W') # %P代表输入框的实时内容
)
e1.place(x=40,y=50)
e2 = tk.Entry(window,
width=50,
textvariable=v_2,
validate='all', # 发生任何变动的时候，就会调用validatecommand
validatecommand=(test_cmd, '%P', '%v', '%W') # %P代表输入框的实时内容
)
e2.place(x=40,y=120)
global active1
active1 = True
def down_list():
try:
ex_name = e2.get() + '.csv'
url = e1.get()
b1.config(state=tk.DISABLED)
result = urlparse(url)
url_parse = list(result) # 元组转为列表
url_parse_fragment = url_parse[-1]
url_parse_fragment=url_parse_fragment.replace('_',',')
url_parse_fragment_l = url_parse_fragment.split(";") # 将字符串转为列表
new_data_list = []
for data in url_parse_fragment_l:
data_1 = re.split('(\w{2})', data, 1)
data_2 = data_1
new_data_list.append(data_2)
new_data_list_len = len(new_data_list)
new_dict = {}
for i in new_data_list:
new_dict[i[1]] = i[2]
base_url = 'http://fund.eastmoney.com/data/FundGuideapi.aspx?'
new_url = base_url + urlencode(new_dict)
html = get_page(new_url)
rusult2 = parse_html1(html)
all_page = int(rusult2[0])
shuju = pd.DataFrame([],
columns=['名称', '基金类型', '管理人', '规模（亿元）', '基金经理', '净值', '日增长率', '成立来', '今年来', '近一周', '近一月',
'近三月', '近六月', '近一年', '近两年', '近三年', '日期', '手续费', '购买起点',
'原手续费']) # 0代码1名称2单位净值3涨跌4基金类型5管理人7-8规模9基金经理12字母代码13基金类型14今年来15近一周16近一月17近三月18近六月19近一年
# 20近两年21近三年25日期26净值27日增长率29手续费30购买起点（元）32原手续费34成立来
for i in range(all_page):
new_dict['pi'] = str(i + 1)
new_dict['sh'] = 'table'
new_url = base_url + urlencode(new_dict)
html_content = get_page(new_url)
result1 = parse_html(html_content)
new_dict['sh'] = 'list'
new_url = base_url + urlencode(new_dict)
html_content = get_page(new_url)
result_list = parse_html_list(html_content)
result_list_up = parse_html_list_up(result_list[0])
for list_1 in result1:
list_1_1 = list(list_1)
list_num = result1.index(list_1)
#print(list_num)
list_1_2 = result_list_up[list_num].split(",") # 通过表一索引提取表二对应字符串并生成列表
list_3 = list_1_1 + list_1_2
print(list_3)
daima = '代码：' + list_3[1]
biao_1 = list_3[0]
biao_2 = list_3[4]
biao_3 = list_3[5]
biao_4 = list_3[7] + list_3[8]
biao_5 = list_3[9]
biao_jin = list_3[2]
biao_6 = list_3[14] + '%'
biao_7 = list_3[15] + '%'
biao_8 = list_3[16] + '%'
biao_9 = list_3[17] + '%'
biao_10 = list_3[18] + '%'
biao_11 = list_3[19] + '%'
biao_12 = list_3[20] + '%'
biao_13 = list_3[21] + '%'
biao_14 = list_3[25]
biao_15 = list_3[27] + '%'
biao_16 = list_3[29]
biao_17 = list_3[30] + '元'
biao_18 = list_3[32]
biao_19 = list_3[34] + '%'
shuju.loc[daima, '名称'] = biao_1
shuju.loc[daima, '基金类型'] = biao_2
shuju.loc[daima, '管理人'] = biao_3
shuju.loc[daima, '规模（亿元）'] = biao_4
shuju.loc[daima, '基金经理'] = biao_5
shuju.loc[daima, '净值'] = biao_jin
shuju.loc[daima, '日增长率'] = biao_15
shuju.loc[daima, '成立来'] = biao_19
shuju.loc[daima, '今年来'] = biao_6
shuju.loc[daima, '近一周'] = biao_7
shuju.loc[daima, '近一月'] = biao_8
shuju.loc[daima, '近三月'] = biao_9
shuju.loc[daima, '近六月'] = biao_10
shuju.loc[daima, '近一年'] = biao_11
shuju.loc[daima, '近两年'] = biao_12
shuju.loc[daima, '近三年'] = biao_13
shuju.loc[daima, '日期'] = biao_14
shuju.loc[daima, '手续费'] = biao_16
shuju.loc[daima, '购买起点'] = biao_17
shuju.loc[daima, '原手续费'] = biao_18
shuju.to_csv(ex_name, encoding='utf-8')
b1.config(state=tk.NORMAL)
except PermissionError:
print('文件名重复并且未关闭，请另外命名或关闭文件')
print('下载结束')
def callback1(event=None):
global window
e1.event_generate('<<Cut>>')
def callback2(event=None):
global window
e1.event_generate('<<Copy>>')
def callback3(event=None):
global window
e1.event_generate('<<Paste>>')
def callback4(event=None):
global window
e2.event_generate('<<Cut>>')
def callback5(event=None):
global window
e2.event_generate('<<Copy>>')
def callback6(event=None):
global window
e2.event_generate('<<Paste>>')
'''创建一个弹出菜单'''
menu = Menu(window,
tearoff=False,
# bg="black",
)
menu1 = Menu(window,
tearoff=False,
# bg="black",
)
menu.add_command(label="剪切", command=callback1)
menu.add_command(label="复制", command=callback2)
menu.add_command(label="粘贴", command=callback3)
menu1.add_command(label="剪切", command=callback4)
menu1.add_command(label="复制", command=callback5)
menu1.add_command(label="粘贴", command=callback6)
def popup(event):
menu.post(event.x_root, event.y_root) # post在指定的位置显示弹出菜单
def popup1(event):
menu1.post(event.x_root, event.y_root) # post在指定的位置显示弹出菜单
e1.bind("<Button-3>", popup) # 绑定鼠标右键,执行popup函数
e2.bind("<Button-3>", popup1)
def start():
global ex_name
global url
ex_name = e2.get() + '.csv'
url = e1.get()
down_list()
b1=tk.Button(window, text='开始下载', width=10,
height=1, command=lambda :thread_it(start))
b1.place(x=500,y=110)
t = tk.Text(window, height=20)
scroll = tk.Scrollbar()
# 放到窗口的右侧, 填充Y竖直方向
scroll.pack(side=tk.RIGHT, fill=tk.Y)
# 两个控件关联
scroll.config(command=t.yview)
t.config(yscrollcommand=scroll.set)
str1 = '万一佣金开户 联系方式 电话&微信：18017439644\n' \
'基金认购费0.1折（银行认购费一般不打折费率平均为1.2%，支付宝天天基金网一般打一折为0.12%。） \n' \
'另有无广客户交流群\n' \
' 专业团队信息发布，理论指导，研报分享。\n' \
' 每日晨报专业老师直播分享财经动态 \n' \
'也可关注公众号：天风散人\n' \
' 下载海量研究报告\n' \
'有脚本，数据分析爬取需求，加微联系'
t.insert(tk.INSERT, str1)
t.place(x=40, y=160)
link = tk.Label(window, text='进入天天基金网站', font=('Arial', 10))
link.place(x=40, y=440)
link1 = tk.Label(window, text='扫码万一佣金开户', font=('宋体', 16))
link1.place(x=610, y=180)
def open_url(event):
webbrowser.open("http://fund.eastmoney.com/daogou", new=0)
link.bind("<Button-1>", open_url)
image_file = tk.PhotoImage(file='img/pic.gif')
canvas = tk.Canvas(window,height=150, width=150)
image = canvas.create_image(75, 0, anchor='n', image=image_file)
canvas.place(x=620, y=250)
window.mainloop()
mystd.restoreStd()
hideConsole()
main_windows()软件效果图片
本文章为转载内容，我们尊重原作者对文章享有的著作权。如有内容错误或侵权问题，欢迎原作者联系我们进行内容更正或删除文章。
