CODEWITHSUNDEEP
pythonuser-interfaceexceptiontkinterpython-requests
A-PSquestions
A-PSquestions

Reputation: 105

requests module MissingSchema error in tkinter GUI due to inability to fill variable before execution of mainloop: How to resolve this?

I'm trying to build a GUI over some existing code and I'm running into a MissingSchema error. I am aware of the general problem but not the best solution.

Basically, before the tkinter mainloop() I'm trying to make a requests module request in order to create a BeautifulSoup object which is needed for a number of functions. However, to make that request I need a filled url variable with a url of the user's choosing; however, this variable cannot be filled until after mainloop() executes. Consequently the requests call fails as the url is empty, giving me the MissingSchema error. You can run the below code to see what I mean:

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()

Sorry if this is a bit large, I tried condensing it as much as possible. I'd like to know what the best way to rectify this error is. I am of the impression that it may be to put the portion regarding making the requests.get() call into a function and use that to return the urlSoup somehow to be used in the functions that need it.

Upvotes: 0

Views: 251

Answers (1)

JacksonPro
JacksonPro

Reputation: 3275

You are attempting to get url even before the user has tried to enter any. So place url request in a function and call it when the Entry widget has text or bind the event handler to a button

Here is a demo.(you can either press the enter key or the run button after inserting text in the Entry widget)

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()

Upvotes: 2

Related Questions