python - 由于在执行主循环之前无法填充变量，在 tkinter GUI 中请求模块 MissingSchema 错误：如何解决这个问题？

Question

我正在尝试在一些现有代码上构建 GUI，但遇到了MissingSchema错误。我知道一般问题，但不是最佳解决方案。

基本上，在 tkinter 之前，mainloop()我试图发出一个requests模块请求，以创建一个 BeautifulSoup 对象，该对象是许多功能所需的。但是，要发出该请求，我需要一个带有用户选择的 url 的填充url变量；mainloop()但是，在执行之后才能填充此变量。因此，requests由于 url 为空，调用失败，给了我MissingSchema错误。你可以运行下面的代码来看看我的意思：

from tkinter import *
from tkinter import scrolledtext as st
import requests
import re
from bs4 import BeautifulSoup

root = Tk()

url_entry = Entry(root)
url = url_entry.get()

log_text = st.ScrolledText(root, state='disabled')

start_button = Button(root, text='Run program', command=lambda: [seo_find_stopwords(urlSoup)])

url_entry.grid(column=0, row=1)
log_text.grid(column=2, row=0, rowspan=3)
start_button.grid(column=1, row=5)

agent = "Mozilla/5.0 (Windows NT 6.3; Win64; x64; rv:10.0) Gecko/20100101 Firefox/10.0"
# attempts to access provided URL, returns errors if unable
try:
    # 'agent' added as part of effort to avoid HTTP Error 403: Forbidden
    url_request = requests.get(url, headers={'User-Agent': agent})
    url_request.raise_for_status()
    urlSoup = BeautifulSoup(url_request.text, 'lxml')
except requests.exceptions.MissingSchema as exc:
    log_text.insert(INSERT, "ERROR: Invalid URL provided. Please try again with a valid URL.")
    raise exc


# searches HTML page title for SEO stop words from stopwords.txt, then provides number and list of present stop words
def seo_find_stopwords(urlSoup):
    stopwords_count = 0
    stopwords_list = []
    if urlSoup.title:
        with open('stopwords.txt', 'r', encoding='utf-8') as file:
            for line in file:
                if re.search(r'\b' + line.rstrip('\n') + r'\b', urlSoup.title.text.casefold()):
                    stopwords_count += 1
                    stopwords_list.append(line.rstrip('\n'))

        if stopwords_count > 0:
            log_text.insert(INSERT, "{0} stop words were found in your page title. If possible, it would be good to "
                        "reduce them. The stop words found are: {1}".format(stopwords_count, stopwords_list))


root.mainloop()

抱歉，如果这有点大，我尝试尽可能地压缩它。我想知道纠正这个错误的最佳方法是什么。我的印象是，它可能是将有关进行requests.get()调用的部分放入一个函数中，并使用它来返回以urlSoup某种方式用于需要它的函数中。

标签： pythonuser-interfaceexceptiontkinterpython-requests

Answer 1

即使在用户尝试输入任何内容之前，您也试图获取 url。因此，将 url 请求放在一个函数中，并在Entry小部件有文本或将事件处理程序绑定到按钮时调用它

这是一个演示。（在小部件中插入文本后，您可以按回车键或运行按钮Entry）

from tkinter import *
import requests
from tkinter import scrolledtext as st
import re
from bs4 import BeautifulSoup

# searches HTML page title for SEO stop words from stopwords.txt, then provides number and list of present stop words
def seo_find_stopwords(urlSoup):
    stopwords_count = 0
    stopwords_list = []
    print('No')
    if urlSoup.title:
        with open('stopwords.txt', 'r', encoding='utf-8') as file:
            
            for line in file:
                if re.search(r'\b' + line.rstrip('\n') + r'\b', urlSoup.title.text.casefold()):
                    stopwords_count += 1
                    stopwords_list.append(line.rstrip('\n'))

        if stopwords_count > 0:
            log_text.insert(INSERT, "{0} stop words were found in your page title. If possible, it would be good to "
                        "reduce them. The stop words found are: {1}".format(stopwords_count, stopwords_list))


def request_url(event=None):
    global urlSoup
    try:
        # 'agent' added as part of effort to avoid HTTP Error 403: Forbidden
        url_request = requests.get(url_entry.get(), headers={'User-Agent': agent})
        url_request.raise_for_status()
        urlSoup = BeautifulSoup(url_request.text, 'lxml')
    except requests.exceptions.MissingSchema as exc:
        log_text.insert(INSERT, "ERROR: Invalid URL provided. Please try again with a valid URL.")
        raise exc    


root = Tk()

urlSoup =''

url_entry = Entry(root)
url_entry.bind('<Return>', request_url)
#url = url_entry.get()

log_text = st.ScrolledText(root, state='disabled')

start_button = Button(root, text='Run program', command=lambda: request_url() or [seo_find_stopwords(urlSoup)])

url_entry.grid(column=0, row=1)
log_text.grid(column=2, row=0, rowspan=3)
start_button.grid(column=1, row=5)

agent = "Mozilla/5.0 (Windows NT 6.3; Win64; x64; rv:10.0) Gecko/20100101 Firefox/10.0"
# attempts to access provided URL, returns errors if unable


root.mainloop()