Python 漂亮的汤爬行和从中间提取文本<；br>；

我的html代码如下所示：

 <br><a href="/drink12xy569.html">Alien Suicide</a>
 <br><a href="/drink792.html">All Jacked Up</a>
 <br><a href="/drink3805.html">All Night Hunter</a>
 <br><a href="/drink796.html">Alley Shooter</a>
 <br><a href="/drink10013.html">Alligator Sperm</a>
 <br><a href="/drink804.html">Almond Delight</a>
 <br><a href="/drink11135.html">Almond Gravy</a>
 <br><a href="/drink7519.html">Almond Joy #2</a>
 <br><a href="/drinks1r2563.html">Almond Kiss</a>
 <br><a href="/drink12xy578.html">Amaretto Pie</a>
 <br><a href="/drink11144.html">Amaretto Sourball</a>
 <br><a href="/drinkp15q144.html">Ambuco Cinnamon Shooter</a>
 <br><a href="/drink835.html">Amenie Mama</a>
 <br><a href="/drink7521.html">American Death</a>

import urllib2
from bs4 import BeautifulSoup
url=[]
for i in range(28):
    url="http://www.drinksmixer.com/cat/3/"
    page = urllib2.urlopen("http://www.drinksmixer.com/cat/3/")
    soup = BeautifulSoup(page.read())
    links=soup.find_all('a')

for link in links:
    if "drink" in link ['href']:
        print link['href']
        print "****\n\n"
        url="http://drinksmixer.com"+link['href']
        page1=urllib2.urlopen(url)
        soup1=BeautifulSoup(page1.read())
        divs=soup1.find('div', {"class":"ingredients"})
        print divs.text.encode("utf-8")

import Tkinter
from Tkinter import *

def show_entry_fields():
   print("Shot Name: %s" % (e1.get()))

master = Tk()
Label(master, text="Shot Name").grid(row=0)

e1 = Entry(master)

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

Button(master, text='Search', command=show_entry_fields).grid(row=3, column=1, sticky=W, pady=4)

mainloop( )

我的gui界面如下所示：

 <br><a href="/drink12xy569.html">Alien Suicide</a>
 <br><a href="/drink792.html">All Jacked Up</a>
 <br><a href="/drink3805.html">All Night Hunter</a>
 <br><a href="/drink796.html">Alley Shooter</a>
 <br><a href="/drink10013.html">Alligator Sperm</a>
 <br><a href="/drink804.html">Almond Delight</a>
 <br><a href="/drink11135.html">Almond Gravy</a>
 <br><a href="/drink7519.html">Almond Joy #2</a>
 <br><a href="/drinks1r2563.html">Almond Kiss</a>
 <br><a href="/drink12xy578.html">Amaretto Pie</a>
 <br><a href="/drink11144.html">Amaretto Sourball</a>
 <br><a href="/drinkp15q144.html">Ambuco Cinnamon Shooter</a>
 <br><a href="/drink835.html">Amenie Mama</a>
 <br><a href="/drink7521.html">American Death</a>

import urllib2
from bs4 import BeautifulSoup
url=[]
for i in range(28):
    url="http://www.drinksmixer.com/cat/3/"
    page = urllib2.urlopen("http://www.drinksmixer.com/cat/3/")
    soup = BeautifulSoup(page.read())
    links=soup.find_all('a')

for link in links:
    if "drink" in link ['href']:
        print link['href']
        print "****\n\n"
        url="http://drinksmixer.com"+link['href']
        page1=urllib2.urlopen(url)
        soup1=BeautifulSoup(page1.read())
        divs=soup1.find('div', {"class":"ingredients"})
        print divs.text.encode("utf-8")

import Tkinter
from Tkinter import *

def show_entry_fields():
   print("Shot Name: %s" % (e1.get()))

master = Tk()
Label(master, text="Shot Name").grid(row=0)

e1 = Entry(master)

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

Button(master, text='Search', command=show_entry_fields).grid(row=3, column=1, sticky=W, pady=4)

mainloop( )

---

我只需要在我提取的信息中实现搜索的帮助。

设计UI并不容易。你的代码几乎没问题。我将它分为多个函数，并添加了您要求的基本搜索

import urllib2
from bs4 import BeautifulSoup
import Tkinter
from Tkinter import *

e1 = None
links = []

def get_drinks():
    global links
    for i in range(28):
        url="http://www.drinksmixer.com/cat/3/" + i
        page = urllib2.urlopen(url)
        soup = BeautifulSoup(page.read())
        links.append(soup.find_all('a'))

def get_recipe(drink_name):
    print drink_name
    for link in links:
        if "drink" in link ['href'] and drink_name in link.contents:
            #print link['href']
            print "****\n\n"
            url="http://drinksmixer.com"+link['href']
            page1=urllib2.urlopen(url)
            soup1=BeautifulSoup(page1.read())
            divs=soup1.find('div', {"class":"ingredients"})
            recipe = divs.text.encode("utf-8")
            return recipe

def show_entry_fields():
    drink_name = e1.get()
    print("Shot Name: %s" % drink_name)
    recipe = get_recipe(drink_name)
    print recipe # or better yet, popup
    # tkMessageBox.showinfo(drink_name, recipe)

def main():
    global e1
    master = Tk()
    Label(master, text="Shot Name").grid(row=0)
    e1 = Entry(master)
    e1.grid(row=0, column=1)
    Button(master, text='Search', command=show_entry_fields).grid(row=3, column=1, sticky=W, pady=4)
    mainloop()

if __name__ == "__main__":
    get_drinks()
    main()

---

用

try:except:

从1开始（

http://www.drinksmixer.com/drink####.html

）如何在gui中而不是python中获得弹出响应？取消注释行

tkMessageBox.showinfo（饮料名称、配方）

这应该可以。@robersam它能工作吗？如果是这样的话，那么你可能想关闭/接受这个答案。确实如此，但我仍然没有得到关于如何查看网站不同页面的帮助。在这里，我编辑了答案，以显示一种可能，即遍历多个页面。如果有很多页面，您应该检查Python的生成器，以便在应用程序运行时在后台加载更多页面/饮料。