You need to enable JavaScript to run this app.
优惠活动
大模型
产品
解决方案
定价
更多

如何用PyInstaller将Scrapy项目GUI打包为exe文件?

问题描述

我想把为Scrapy项目开发的GUI程序用PyInstaller打包成exe文件,之前从没使用过该工具。已在Scrapy虚拟环境(venv)中安装PyInstaller并尝试打包,但生成的exe运行时控制台闪退,无法查看错误信息。搜索网络及Stack Overflow的解决方案后仍未匹配到自身问题,现将相关代码附上:

Spider代码

import scrapy
import pandas as pd
from twisted.internet.error import DNSLookupError


class CheckSpider(scrapy.Spider):
    name = 'check'

    def read_xl(df):
        df = pd.read_excel('url.xlsx')
        return df['url'].tolist()

    def start_requests(self):
        for value in self.read_xl():
            yield scrapy.Request(
                url=value,
                callback= self.parse,
                errback=self.parse_error
            )
        return super().start_requests()

    def parse_error(self, failure):
        if failure.check(DNSLookupError):
            request = failure.request
            yield {
                'URL': request.url,
                'Status': failure.value
            }

    def parse(self, response):
        if response.request.meta.get('redirect_urls'):
            yield {
                'URL': response.request.meta.get('redirect_urls')[0],
                'Redireted URL': response.request.url,
                'Status': response.status
            }
        else:
            yield {
                'URL': response.url,
                'Redireted URL': response.request.url,
                'Status': response.status
            }

GUI代码

from tkinter import *
from tkinter import messagebox
from tkinter import filedialog
from scrapy.utils import project
from scrapy import spiderloader
from scrapy.utils.log import configure_logging
from scrapy.crawler import CrawlerRunner
from twisted.internet import reactor
import threading

def get_spiders():
    settings = project.get_project_settings()
    spider_loader = spiderloader.SpiderLoader.from_settings(settings)
    return spider_loader.list()

def browse_button():
    global folder_path
    folder_path = filedialog.askdirectory()
    folder_path_entry.delete(0, END)
    folder_path_entry.insert(0, folder_path)
    return folder_path

def execute_spider():
    chosen_spider = spider_text.get()
    chosen_feed = feed_text.get()
    if dataset_entry.get() == '' or chosen_feed not in ['csv', 'json']:
        messagebox.showerror('Error', 'All entries are required')
        return
    try:
        feed_uri = f'file:///{folder_path}/{dataset_entry.get()}.{chosen_feed}'
    except:
        messagebox.showerror('Error', 'All entries are required')

    settings = project.get_project_settings()
    # settings.set('FEED_URI', feed_uri)
    # settings.set('FEED_TYPE', chosen_feed)
    settings.set("FEEDS", {
        f'output.{chosen_feed}': {
            'format': chosen_feed,
            'encoding': 'utf8'
        }
    })

    configure_logging()
    runner = CrawlerRunner(settings)
    runner.crawl(chosen_spider)

    reactor.run(installSignalHandlers=False)

def start_execute_thread(event):
    global execute_thread
    execute_thread = threading.Thread(target=execute_spider, daemon=True)
    execute_thread.start()
    app.after(10, check_execute_thread)

def check_execute_thread():
    if execute_thread.is_alive():
        app.after(10, check_execute_thread)


app = Tk()
# app title
app.title('Check Website Status')
# app size
app.geometry('300x200')
app.resizable(False, False)

# app label
spider_label = Label(app, text='Choose a spider')
spider_label.grid(row=0, column=0, sticky=W, pady=10, padx=10)

# Choose Spider
spider_text = StringVar(app)
spider_text.set('Choose a spider')
spiders = [spider for spider in get_spiders()]

spiders_dropdown = OptionMenu(app, spider_text, *spiders)
spiders_dropdown.grid(row=0, column=1, columnspan=2)

# Feed Type
feed_label = Label(app, text='Choose a feed')
feed_label.grid(row=1, column=0, sticky=W, pady=10, padx=10)

feed_text = StringVar(app)
feed_text.set('Choose a feed')
feeds = ['csv', 'json']

feed_dropdown = OptionMenu(app, feed_text, *feeds)
feed_dropdown.grid(row=1, column=1, columnspan=2)

# path entry
folder_path_text = StringVar(app)
folder_path_entry = Entry(app, textvariable=folder_path_text)
folder_path_entry.grid(row=2, column=0, pady=10, padx=10)

# Dataset entry
dataset_text = StringVar(app)
dataset_entry = Entry(app, textvariable=dataset_text, width=10)
dataset_entry.grid(row=2, column=1, pady=10, padx=10)

browse_btn = Button(app, text='Browse', command=browse_button)
browse_btn.grid(row=2, column=2,)

execute_btn = Button(app,text='Execute', command=lambda: start_execute_thread(None))
execute_btn.grid(row=3, column=0, columnspan=3)

app.mainloop()

注:此前我曾因该脚本的GUI相关问题向@Alexander求助过。

内容的提问来源于stack exchange,提问作者Raisul Islam

相关产品推荐
方舟 Agent Plan

超全模态模型 × Harness 升级,最新支持 Deepseek-V4.1-Flash、GLM-5.3 系列、Doubao-Seedream-5.0-pro、Kimi-K3 (部分), 限时 9.9 元起

最近更新时间:2026.08.13 20:20:35