Converting html to text with Python

Question

I am trying to convert an html block to text using Python.

Input:

        
                      

              相关标签:
       
      

Answer 1

You can use a regular expression, but it's not recommended. The following code removes all the HTML tags in your data, giving you the text:

import re

data = """<div class="body"><p><strong></strong></p>
<p><strong></strong>Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa</p>
<p>Consectetuer adipiscing elit. <a href="http://example.com/" target="_blank" class="source">Some Link</a> Aenean commodo ligula eget dolor. Aenean massa</p>
<p>Aenean massa.Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa</p>
<p>Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa</p>
<p>Consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa</p></div>"""

data = re.sub(r'<.*?>', '', data)

print(data)

Output

Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa
Consectetuer adipiscing elit. Some Link Aenean commodo ligula eget dolor. Aenean massa
Aenean massa.Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa
Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa
Consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa

Answer 2

gazpacho might be a good choice for this!

Input:

from gazpacho import Soup

html = """\
<div class="body"><p><strong></strong></p>
<p><strong></strong>Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa</p>
<p>Consectetuer adipiscing elit. <a href="http://example.com/" target="_blank" class="source">Some Link</a> Aenean commodo ligula eget dolor. Aenean massa</p>
<p>Aenean massa.Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa</p>
<p>Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa</p>
<p>Consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa</p></div>
"""

Output:

text = Soup(html).strip(whitespace=False) # to keep "\n" characters intact
print(text)

Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa
Consectetuer adipiscing elit. Some Link Aenean commodo ligula eget dolor. Aenean massa
Aenean massa.Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa
Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa
Consectetuer adipiscing elit. Aenean commodo ligula eget dolor. Aenean massa

Answer 3

The '\n' places a newline between the paragraphs.

from bs4 import Beautifulsoup

soup = Beautifulsoup(text)
print(soup.get_text('\n'))

Answer 4

I liked @FrBrGeorge's no dependency answer so much that I expanded it to only extract the body tag and added a convenience method so that HTML to text is a single line:

from abc import ABC
from html.parser import HTMLParser


class HTMLFilter(HTMLParser, ABC):
    """
    A simple no dependency HTML -> TEXT converter.
    Usage:
          str_output = HTMLFilter.convert_html_to_text(html_input)
    """
    def __init__(self, *args, **kwargs):
        self.text = ''
        self.in_body = False
        super().__init__(*args, **kwargs)

    def handle_starttag(self, tag: str, attrs):
        if tag.lower() == "body":
            self.in_body = True

    def handle_endtag(self, tag):
        if tag.lower() == "body":
            self.in_body = False

    def handle_data(self, data):
        if self.in_body:
            self.text += data

    @classmethod
    def convert_html_to_text(cls, html: str) -> str:
        f = cls()
        f.feed(html)
        return f.text.strip()           

See comment for usage.

This converts all of the text inside the body, which in theory could include style and script tags. Further filtering could be achieved by extending the pattern of as shown for body -- i.e. setting instance variables in_style or in_script.

Answer 5

It's possible using python standard html.parser:

from html.parser import HTMLParser

class HTMLFilter(HTMLParser):
    text = ""
    def handle_data(self, data):
        self.text += data

f = HTMLFilter()
f.feed(data)
print(f.text)

Answer 6

I was in need of a way of doing this on a client's system without having to download additional libraries. I never found a good solution, so I created my own. Feel free to use this if you like.

import urllib 

def html2text(strText):
    str1 = strText
    int2 = str1.lower().find("<body")
    if int2>0:
       str1 = str1[int2:]
    int2 = str1.lower().find("</body>")
    if int2>0:
       str1 = str1[:int2]
    list1 = ['<br>',  '<tr',  '<td', '</p>', 'span>', 'li>', '</h', 'div>' ]
    list2 = [chr(13), chr(13), chr(9), chr(13), chr(13),  chr(13), chr(13), chr(13)]
    bolFlag1 = True
    bolFlag2 = True
    strReturn = ""
    for int1 in range(len(str1)):
      str2 = str1[int1]
      for int2 in range(len(list1)):
        if str1[int1:int1+len(list1[int2])].lower() == list1[int2]:
           strReturn = strReturn + list2[int2]
      if str1[int1:int1+7].lower() == '<script' or str1[int1:int1+9].lower() == '<noscript':
         bolFlag1 = False
      if str1[int1:int1+6].lower() == '<style':
         bolFlag1 = False
      if str1[int1:int1+7].lower() == '</style':
         bolFlag1 = True
      if str1[int1:int1+9].lower() == '</script>' or str1[int1:int1+11].lower() == '</noscript>':
         bolFlag1 = True
      if str2 == '<':
         bolFlag2 = False
      if bolFlag1 and bolFlag2 and (ord(str2) != 10) :
        strReturn = strReturn + str2
      if str2 == '>':
         bolFlag2 = True
      if bolFlag1 and bolFlag2:
        strReturn = strReturn.replace(chr(32)+chr(13), chr(13))
        strReturn = strReturn.replace(chr(9)+chr(13), chr(13))
        strReturn = strReturn.replace(chr(13)+chr(32), chr(13))
        strReturn = strReturn.replace(chr(13)+chr(9), chr(13))
        strReturn = strReturn.replace(chr(13)+chr(13), chr(13))
    strReturn = strReturn.replace(chr(13), '\n')
    return strReturn


url = "http://www.theguardian.com/world/2014/sep/25/us-air-strikes-islamic-state-oil-isis"    
html = urllib.urlopen(url).read()    
print html2text(html)