Python + BeautifulSoup: How to get wrapper out of HTML based on text?

Question

Would like to get the wrapper of a key text. For example, in HTML:

…
chicken
apple         


        
      

Answer 1

# coding: utf-8

html_doc = """


  
    
    
  
  
    

        

            

                

                    

                      
My chicken has ONE leg :P
                        

                            

                              
eat me
                                

                                
                            
                        
                    
                
            
        
    
  
"""

from bs4 import BeautifulSoup as BS
import re
soup = BS(html_doc, "lxml")


# (tag -> text) direction is pretty obvious that way
tag = soup.find('div', class_="chicken")
tag2 = soup.find('div', {'id':"chicken_surname"})
print('\n###### by_cls:')
print(tag)
print('\n###### by_id:')
print(tag2)

# but can be tricky when need to find tag by substring
tag_by_str = soup.find(string="eat me")
tag_by_sub = soup.find(string="eat")
tag_by_resub = soup.find(string=re.compile("eat"))
print('\n###### tag_by_str:')
print(tag_by_str)
print('\n###### tag_by_sub:')
print(tag_by_sub)
print('\n###### tag_by_resub:')
print(tag_by_resub)

# there are more than one way to access underlying strings
# both are different - see results
tag = soup.find('p')

print('\n###### .text attr:')
print( tag.text, type(tag.text) )

print('\n###### .strings generator:')
for s in tag.strings:   # strings is an generator object
    print s, type(s)

# note that .strings generator returns list of bs4.element.NavigableString elements
# so we can use them to navigate, for example accessing their parents:
print('\n###### NavigableString parents:')
for s in tag.strings:  
    print s.parent

# or even grandparents :)
print('\n###### grandparents:')
for s in tag.strings:  
    print s.parent.parent