Last active
August 29, 2015 14:14
-
-
Save 7stud/ac22c8d9c01097ed9f99 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
data.txt: | |
------------------------------ | |
<h1>1</h1> <!-- Level One --> | |
<h4>1.1</h4> <!-- Level Two --> | |
<div class='x'>1.1.1</div> <!-- Level Three --> | |
<div class='x'>1.1.2</div> | |
<div class='x'>1.1.3</div> | |
<div class='x'>1.1.4</div> | |
<h4>1.2</h4> | |
<div class='x'>1.2.1</div> | |
<div class='x'>1.2.2</div> | |
<div class='x'>1.2.3</div> | |
<div class='x'>1.2.4</div> | |
<h4>1.3</h4> | |
<div class='x'>1.3.1</div> | |
<div class='x'>1.3.2</div> | |
<div class='x'>1.3.3</div> | |
<div class='x'>1.3.4</div> | |
<h4>1.4</h4> | |
<div class='x'>1.4.1</div> | |
<div class='x'>1.4.2</div> | |
<div class='x'>1.4.3</div> | |
<div class='x'>1.4.4</div> | |
<h1>2</h1> | |
<h4>2.1</h4> | |
<div class='x'>2.1.1</div> | |
<div class='x'>2.1.2</div> | |
<div class='x'>2.1.3</div> | |
<div class='x'>2.1.4</div> | |
<h4>2.2</h4> | |
<div class='x'>2.2.1</div> | |
<div class='x'>2.2.2</div> | |
<div class='x'>2.2.3</div> | |
<div class='x'>2.2.4</div> | |
<h4>2.3</h4> | |
<div class='x'>2.3.1</div> | |
<div class='x'>2.3.2</div> | |
<div class='x'>2.3.3</div> | |
<div class='x'>2.3.4</div> | |
<h4>2.4</h4> | |
<div class='x'>2.4.1</div> | |
<div class='x'>2.4.2</div> | |
<div class='x'>2.4.3</div> | |
<div class='x'>2.4.4</div> | |
---------------------- | |
from bs4 import BeautifulSoup | |
with open('data.txt') as f: | |
html = f.read() | |
soup = BeautifulSoup(html) | |
elmt = soup.find('h1') | |
h1_text = elmt.text | |
while True: | |
elmt = elmt.next_sibling | |
if not elmt: break #then no more tags | |
tag_name = getattr(elmt, 'name', None) #Tags have names like 'h1', 'h4', 'div'. If the tag | |
#does not have a name, e.g. a Comment, return None | |
if not tag_name: continue #Skip the Comment's in your html | |
if tag_name == 'h1': | |
h1_text = elmt.text | |
elif tag_name == 'h4': | |
h4_text = elmt.text | |
elif tag_name == 'div': | |
print("{}:{}:{}".format(h1_text, h4_text, elmt.text)) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment