1

我正在处理我的代码中的一些错误，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，有代码，它连接到谷歌，并搜索表单（souptrainer），一切正常，但问题是这向我显示了这个错误：

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，但我不明白如何修改代码以使其工作。

谢谢大家！

4

1 回答 1

2

是的，findAll 返回一个 ResultSet，它是一种列表。因此，您可以选择一个值或遍历它们。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)
于 2013-06-24T00:58:39.640 回答