Beautifulsoup'ResultSet'对象没有'findAll'属性时出错

Question

我在处理代码中的一些错误，这里是：

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
from BeautifulSoup import BeautifulSoup as beatsop
from BeautifulSoup import SoupStrainer as sopstrain
import urllib2

def html_parser(html_data):
    html_proc = beatsop(html_data)
    onlyforms = sopstrain("form")
    forms1 = html_proc.findAll(onlyforms)
    txtinput = forms1.findAll('input', {'type': 'text'})
    #We take the forms that aren't text
    listform = ["radio", "checkbox", "password", "file", "image", "hidden"]
    otrimput = forms1.findAll('input', {'type': listform})
    # we seach for names in text forms
    for e_name in txtinput:
        names = e_name['name']
    #we seach for value in otrimput
    for e_value in otrimput:
        value1 = e_value.get('value')
        if value1:
            pass
        else:
            print('{} there is no value.'.format(e_value))

html_data = urllib2.urlopen("http://www.google.com")
html_parser(html_data)

所以，这里有代码，它连接到google，seach for the forms（soupstrainer），一切正常，但问题是这显示了这个错误：

txtinput = forms1.findAll('input', {'type': 'text'})
AttributeError: 'ResultSet' object has no attribute 'findAll'

我认为错误在于forms1数据是一个列表，但是我不理解如何修改代码使其工作。

谢谢大家！

Answer 1

是的，findAll返回一个ResultSet，它是一种列表类型。所以你可以选择一个值或者遍历它们。下面的代码显示了迭代。

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
from BeautifulSoup import BeautifulSoup as beatsop
from BeautifulSoup import SoupStrainer as sopstrain
import urllib2

def html_parser(html_data):
    html_proc = beatsop(html_data)
    onlyforms = sopstrain("form")
    forms1 = html_proc.findAll(onlyforms)
    for found_form in forms1:
        txtinput = found_form.findAll('input', {'type': 'text'})
        #We take the forms that aren't text
        listform = ["radio", "checkbox", "password", "file", "image", "hidden"]
        otrimput = found_form.findAll('input', {'type': listform})
        # we seach for names in text forms
        for e_name in txtinput:
            names = e_name['name']
        #we seach for value in otrimput
        for e_value in otrimput:
            value1 = e_value.get('value')
            if value1:
                pass
            else:
                print('{} there is no value.'.format(e_value))

html_data = urllib2.urlopen("http://www.google.com")
html_parser(html_data)