使用 tkinter 输入一个变量,被调用

Using tkinter to input into a variable, to be called

我目前正在开发一种类似爬虫的程序,它将进入维基百科页面,并以其当前形式从页面中抓取参考文献。

我想要一个允许用户输入维基百科页面的图形用户界面。我希望将输入附加到 selectWikiPage 变量,但到目前为止运气不好。

下面是我当前的代码。

import requests
from bs4 import BeautifulSoup
import re
from tkinter import *

#begin tkinter gui
def show_entry_fields():
   print("Wikipedia URL: %s" % (e1.get()))
   e1.delete(0,END)
master = Tk()
Label(master, text="Wikipedia URL").grid(row=0)
e1 = Entry(master)
e1.insert(10,"http://en.wikipedia.org/wiki/randomness")
e1.grid(row=0, column=1)
Button(master, text='Scrape', command=master.quit).grid(row=3, column=0, sticky=W, pady=4)
mainloop( )

session = requests.Session()
selectWikiPage = input(print("Please enter the Wikipedia page you wish to scrape from"))
if "wikipedia" in selectWikiPage:
    html = session.post(selectWikiPage)
    bsObj = BeautifulSoup(html.text, "html.parser")

    findReferences = bsObj.find('ol', {'class': 'references'}) #isolate refereces section of page
    href = BeautifulSoup(str(findReferences), "html.parser")
    links = [a["href"] for a in href.find_all("a", href=True)]

    for link in links:
        print("Link: " + link)

else:
    print("Error: Please enter a valid Wikipedia URL")

非常感谢。

这是一个基于您的代码的小型示例;它允许使用输入字段捕获要访问的 wiki 页面的值,并将其打印在控制台上。
然后您可以使用此 url 继续您的抓取。

from tkinter import *

def m_quit():
    global wiki_url
    wiki_url += e1.get() + '/'
    print('quitting')
    master.destroy()

wiki_url = 'http://en.wikipedia.org/wiki/'    

master = Tk()
Label(master, text="Wikipedia URL").grid(row=0)

e1 = Entry(master)
e1.grid(row=0, column=1)

Button(master, text='Scrape', command=m_quit).grid(row=3, column=0, sticky=W, pady=4)

mainloop()

print(wiki_url)

代码几乎是正确的。一些修改就足够了。希望这可以帮助。如果您需要任何进一步的说明,请发表评论。

    import requests
    from bs4 import BeautifulSoup
    import re
    from tkinter import *


    # you can declare selectWikiPage and master to be global and then avoid passing them around

    # begin tkinter gui
    def show_entry_fields():
        print("Wikipedia URL: %s" % (e1.get()))
        e1.delete(0, END)

    #utility which selects all the text from start to end in widget
    def select_all(event=None):
        event.widget.select_range(0, 'end')
        return 'break'


    #the code is same, just obtained the URL from the widget using get()

    def custom_scrape(e1, master):
        session = requests.Session()
        # selectWikiPage = input("Please enter the Wikipedia page you wish to scrape from")
        selectWikiPage = e1.get()
        if "wikipedia" in selectWikiPage:
            html = session.post(selectWikiPage)
            bsObj = BeautifulSoup(html.text, "html.parser")
            findReferences = bsObj.find('ol', {'class': 'references'})  # isolate refereces section of page
            href = BeautifulSoup(str(findReferences), "html.parser")
            links = [a["href"] for a in href.find_all("a", href=True)]
            for link in links:
                print("Link: " + link)
        else:
            print("Error: Please enter a valid Wikipedia URL")

        master.quit()


    master = Tk()
    Label(master, text="Wikipedia URL").grid(row=0)
    e1 = Entry(master)

    #bind ctrl+a for selecting all the contents of Entry widget
    e1.bind('<Control-a>', select_all)
    e1.insert(10, "Enter a wikipedia URL")
    e1.grid(row=0, column=1)

    #here, command attribute takes a lambda which itself doesnot take any args,
    #but in turn calls another function which accepts
    #arguments
    #Refer to:  for details

    Button(master, text='Scrape', command=lambda: custom_scrape(e1, master)).grid(row=3, column=0, sticky=W, pady=4)
    mainloop()