python - 我如何从 HTML 文件中提取我需要的数据？

Question

这是我的 HTML:

p_tags = '''<p class="foo-body">
  <font class="test-proof">Full name</font> Foobar<br />
  <font class="test-proof">Born</font> July 7, 1923, foo, bar<br />
  <font class="test-proof">Current age</font> 27 years 226 days<br />
  <font class="test-proof">Major teams</font> <span style="white-space: nowrap">Japan,</span> <span style="white-space: nowrap">Jakarta,</span> <span style="white-space: nowrap">bazz,</span> <span style="white-space: nowrap">foo,</span> <span style="white-space: nowrap">foobazz</span><br />
  <font class="test-proof">Also</font> bar<br />
  <font class="test-proof">foo style</font> hand <br />
  <font class="test-proof">bar style</font> ball<br />
  <font class="test-proof">foo position</font> bak<br />
  <br class="bar" />
</p>'''

这是我的 Python 代码，使用 Beautiful Soup:

def get_info(p_tags):
    """Returns brief information."""

    head_list = []
    detail_list = []
    # This works fine
    for head in p_tags.findAll('font', 'test-proof'):
        head_list.append(head.contents[0])

    # Some problem with this?
    for index in xrange(2, 30, 4):
        detail_list.append(p_tags.contents[index])


    return dict([(l, detail_list[head_list.index(l)]) for l in head_list])

我从 HTML 中获得了正确的 head_list，但 detail_list 不工作。

head_list = [u'Full name', u'Born', u'Current age', u'Major teams', u'Also', u'foo style', u'bar style', u'foo position']

我想要这样的东西

{  'Full name': 'Foobar',   'Born': 'July 7, 1923, foo, bar',   'Current age': '78 years 226 days',   'Major teams': 'Japan, Jakarta, bazz, foo, foobazz',   'Also': 'bar',   'foo style': 'hand',   'bar style': 'ball',   'foo position': 'bak'}

任何帮助都将不胜感激。提前致谢。

Answer 1

在我意识到你在使用“BeautifulSoup ”之前我就开始回答这个问题了，但我认为这是一个解析器，它适用于你使用 HTMLParser 库编写的示例字符串

from HTMLParser import HTMLParser

results = {}
class myParse(HTMLParser):

   def __init__(self):
      self.state = ""
      HTMLParser.__init__(self)

   def handle_starttag(self, tag, attrs):
      attrs = dict(attrs)
      if tag == "font" and attrs.has_key("class") and attrs['class'] == "test-proof":
         self.state = "getKey"

   def handle_endtag(self, tag):
      if self.state == "getKey" and tag == "font":
         self.state = "getValue"

   def handle_data(self, data):
      data = data.strip()
      if not data:
         return
      if self.state == "getKey":
         self.resultsKey = data
      elif self.state == "getValue":
         if results.has_key(self.resultsKey):
            results[self.resultsKey] += " " + data 
         else: 
            results[self.resultsKey] = data


if __name__ == "__main__":
   p_tags = """<p class="foo-body">  <font class="test-proof">Full name</font> Foobar<br />  <font class="test-proof">Born</font> July 7, 1923, foo, bar<br />  <font class="test-proof">Current age</font> 27 years 226 days<br />  <font class="test-proof">Major teams</font> <span style="white-space: nowrap">Japan,</span> <span style="white-space: nowrap">Jakarta,</span> <span style="white-space: nowrap">bazz,</span> <span style="white-space: nowrap">foo,</span> <span style="white-space: nowrap">foobazz</span><br />  <font class="test-proof">Also</font> bar<br />  <font class="test-proof">foo style</font> hand <br />  <font class="test-proof">bar style</font> ball<br />  <font class="test-proof">foo position</font> bak<br />  <br class="bar" /></p>"""
   parser = myParse()
   parser.feed(p_tags)
   print results

给出结果:

{'foo position': 'bak', 
'Major teams': 'Japan, Jakarta, bazz, foo, foobazz', 
'Also': 'bar', 
'Current age': '27 years 226 days', 
'Born': 'July 7, 1923, foo, bar' , 
'foo style': 'hand', 
'bar style': 'ball', 
'Full name': 'Foobar'}