提取两个P之间的文本

合并您的代码。

import os
from simplified_scrapy.simplified_doc import SimplifiedDoc
directory ='C:/Research syntheses - Meta analysis/SeekingAlpha'
for filename in os.listdir(directory):
  if filename.endswith('.html'):
    fname = os.path.join(directory,filename)
    with open(fname, 'r') as f:
      page=f.read()
      doc = SimplifiedDoc(page)
      headline = doc.select('div#article_info>span#about_primary_stocks>a>text()')
      div = doc.select('div#article_participants')
      if not div: continue
      ps = div.getElements('p',start='<strong>Executives</strong>',end='<strong>Analysts</strong>')
      Executives = [p.text.split('-')[0].strip() for p in ps]
      ps = div.getElements('p',start='<strong>Analysts</strong>')
      Analysts = [p.text.split('-')[0].strip() for p in ps]
      print (headline)
      print (Executives)
      print (Analysts)

以下代码是一个示例。

from simplified_scrapy.simplified_doc import SimplifiedDoc
html = '''
<div class="page_header_email_alerts" id="page_header">
  <h1>
    <span itemprop="headline">Wabash National's (WNC) CEO Richard Giromini on Q4 2014 Results - Earnings Call Transcript</span>
  </h1>
  <div id="article_info">
    <div class="article_info_pos">
      <span itemprop="datePublished" content="2015-02-04T21:48:03Z">Feb.  4, 2015  4:48 PM ET</span>
      <span id="title_article_comments"></span>
      <span class="print_hide"><span class="print_hide">&nbsp;|&nbsp;</span> <span>About:</span> <span id="about_primary_stocks"><a title="Wabash National Corporation" href="/symbol/WNC" sasource="article_primary_about_trc">Wabash National Corporation (WNC)</a></span></span>
      <span class="author_name_for_print">by: SA Transcripts</span>
        <span id="second_line_wrapper"></span>
    </div>
  </div>
</div>
<div class="content_part hid" id="article_participants">
<p>Wabash National Corporation (NYSE:<a title="" href="http://seekingalpha.com/symbol/wnc">WNC</a>)</p><p>Q4 2014 <span class="transcript-search-span" style="background-color: yellow;">Earnings</span> Conference <span class="transcript-search-span" style="background-color: rgb(243, 134, 134);">Call</span></p><p>February 04, 2015 10:00 AM ET</p>
<p><strong>Executives</strong></p>
<p>Mike Pettit - Vice President of Finance and Investor Relations</p>
<p>Richard Giromini - President and Chief Executive Officer</p>
<p>Jeffery Taylor - Senior Vice President and Chief Financial Officer</p>
<p><strong>Analysts</strong></p>
<p>Jeffery Taylor - Senior Vice President and Chief Financial Officer</p>
</div>
'''
doc = SimplifiedDoc(html)
headline = doc.select('div#article_info>span#about_primary_stocks>a>text()')
div = doc.select('div#article_participants')
ps = div.getElements('p',start='<strong>Executives</strong>',end='<strong>Analysts</strong>')
Executives = [p.text.split('-')[0].strip() for p in ps]
ps = div.getElements('p',start='<strong>Analysts</strong>')
Analysts = [p.text.split('-')[0].strip() for p in ps]

print (headline)
print (Executives)
print (Analysts)

结果：

Wabash National Corporation (WNC)
[u'Mike Pettit', u'Richard Giromini', u'Jeffery Taylor']
[u'Jeffery Taylor']

这里有更多示例：https : //github.com/yiyedata/simplified-scrapy-demo/tree/master/doc_examples