Python: Deleting all divs without class - python

I want to delete all divs without classes (but not the content that is in the div).
My input
<h1>Test</h1>
<div>
<div>
<div class="test">
<p>abc</p>
</div>
</div>
</div>
The output I want
<h1>Test</h1>
<div class="test">
<p>abc</p>
</div>
My try 1
Based on "Deleting a div with a particular class":
from bs4 import BeautifulSoup
soup = BeautifulSoup('<h1>Test</h1><div><div><div class="test"><p>abc</p></div></div></div>', 'html.parser')
for div in soup.find_all("div", {'class':''}):
div.decompose()
print(soup)
# <h1>Test</h1>
My try 2
from htmllaundry import sanitize
myinput = '<h1>Test</h1><div><div><div class="test"><p>abc</p></div></div></div>'
myoutput = sanitize(myinput)
print myoutput
# <p>Test</p><p>abc</p> instead of <h1>Test</h1><div class="test"><p>abc</p></div>
My try 3
Based on "Clean up HTML in python"
from lxml.html.clean import Cleaner
def sanitize(dirty_html):
cleaner = Cleaner(remove_tags=('font', 'div'))
return cleaner.clean_html(dirty_html)
myhtml = '<h1>Test</h1><div><div><div class="test"><p>abc</p></div></div></div>'
print(sanitize(myhtml))
# <div><h1>Test</h1><p>abc</p></div>
My try 4
from html_sanitizer import Sanitizer
sanitizer = Sanitizer() # default configuration
output = sanitizer.sanitize('<h1>Test</h1><div><div><div class="test"><p>abc</p></div></div></div>')
print(output)
# <h1>Test</h1><p>abc</p>
Problem: A div element is used to wrap the HTML fragment for the parser, therefore div tags are not allowed. (Source: Manual)

If you want to exclude div without class, preserving its content:
from bs4 import BeautifulSoup
markup = '<h1>Test</h1><div><div><div class="test"><p>abc</p></div></div></div>'
soup = BeautifulSoup(markup,"html.parser")
for tag in soup.find_all():
empty = tag.name == 'div' and not(tag.has_attr('class'))
if not(empty):
print(tag)
Output:
<h1>Test</h1>
<div class="test"><p>abc</p></div>
<p>abc</p>

Please checkout this.
from bs4 import BeautifulSoup
data="""
<div>
<div>
<div class="test">
<p>abc</p>
</div>
</div>
</div>
"""
soup = BeautifulSoup(data, features="html5lib")
for div in soup.find_all("div", class_=True):
print(div)

Related

I want to get the value of multiple ids inside an a tag that resides in a div

Here's the HTML code:
<div class="sizeBlock">
<div class="size">
<a class="selectSize" id="44526" data-size-original="36.5">36.5</a>
</div>
<div class="size inactive active">
<a class="selectSize" id="44524" data-size-original="40">40</a>
</div>
<div class="size ">
<a class="selectSize" id="44525" data-size-original="40.5">40.5</a>
</div>
</div>
I want to get the values of the id tag and the data-size-original.
Here's my code:
for sizeBlock in soup.find_all('a', class_="selectSize"):
aid = sizeBlock.get('id')
size = sizeBlock.get('data-size-us')
The problem is that it gets the values of other ids that have the same class "selectSize".
I think this is what you want. You won't have ids and size from data in div class='size inactive active'
for sizeBlock in soup.select('div.size a.selectSize'):
aid = sizeBlock.get('id')
size = sizeBlock.get('data-size-us')
Already answered here How to Beautiful Soup (bs4) match just one, and only one, css class
Use soup.select. Here's a simple test:
from bs4 import BeautifulSoup
html_doc = """<div class="size">
<a class="selectSize otherclass" id="44526" data-ean="0193394075362" " data-tprice="" data-sku="1171177-36.5" data-size-original="36.5">5</a>
</div>"""
soup = BeautifulSoup(html_doc, 'html.parser')
#for sizeBlock in soup.find_all('a', class_= "selectSize"): # this would include the anchor
for sizeBlock in soup.select("a[class='selectSize']"):
aid = sizeBlock.get('id')
size = sizeBlock.get('data-size-original')
print aid, size

I want to find a <span> tag that resides inside a <h1> tag that contains multiple <span> tags and get the text inside it

What I want to do is select the second span and grab its text to print it.
Below is the HTML code and BeautifulSoup code
#HTML code
<h1 id="productTitle">
<a href="https://www.example.com/product/">
<span id="productBrand">BRAND</span>
</a>
<span>PRODUCT TITLE </span>
</h1>
#BeautifulSoup code
for h1 in soup.find_all('h1', id="productTitle"):
productTitle = h1.find('span').text
print(productTitle)
Hopefully, not always, id should be unique meaning find_all is likely not required.
With bs4 4.7.1+ you can use :not to exclude the child span with an id
from bs4 import BeautifulSoup as bs
html = '''<h1 id="productTitle">
<a href="https://www.example.com/product/">
<span id="productBrand">BRAND</span>
</a>
<span>PRODUCT TITLE </span>
</h1>
'''
soup = bs(html, 'lxml')
print(soup.select_one('#productTitle span:not([id])').text)
You could also nth-child
print(soup.select_one('#productTitle span:nth-child(2)').text)
or
print(soup.select_one('#productTitle span:nth-child(even)').text)
or even an immediate sibling combinator to get span after child a
print(soup.select_one('#productTitle a + span').text)
or chained next_sibling
print(soup.select_one('#productTitle a').next_sibling.next_sibling.text)
This gets all the fields you need within an h1 tag :
Python Code :
from bs4 import BeautifulSoup
text = '''
<h1 id="productTitle">
<a href="https://www.example.com/product/">
<span id="productBrand">BRAND</span>
</a>
<span>PRODUCT TITLE </span>
</h1>
'''
soup = BeautifulSoup(text,features='html.parser')
#BeautifulSoup code
for h1 in soup.find_all('h1', id="productTitle"):
spans = h1.find_all('span')
print('productBrand == > {}'.format(spans[0].text))
print('productTitle == > {}'.format(spans[1].text))
Get All Spans withing the h1 :
for h1 in soup.find_all('h1', id="productTitle"):
for i,span in enumerate(h1.find_all('span')):
print('span {} == > {}'.format(i,span.text))
Demo :
Here

Find tag with certain child tag using bs4 python

I have an html in the below format.
<div class="consider">
<div class="row">
<p>Text1</p>
</div>
</div>
<div class="consider">
<h2>Hello</h2>
</div>
<div class="Consider">
<div class="row">
<p>Text2
</div>
</div>
I want to get the tag div only where its child tag(div) has class as "row"
this is how you can access it :
from bs4 import BeautifulSoup
content = '<div class="consider"><div class="row"><p>Text1</p></div></div><div class="consider"><h2>Hello</h2></div><div class="Consider"><div class="row"><p>Text2</p></div></div>'
soup = BeautifulSoup(content, 'lxml')
for div in soup.find_all('div', class_='row'):
if div.parent.name == "div":
#do whatever you want with div.parent which is the element you want.
With select('div > div.row') we select all div tags with class row as direct children of div tag and then through list comprehension we select all parents of these tags:
data = '<div class="consider"><div class="row"><p>Text1</p></div></div><div class="consider"><h2>Hello</h2></div><div class="Consider"><div class="row"><p>Text2</p></div></div>'
from bs4 import BeautifulSoup
soup = BeautifulSoup(data, 'lxml')
divs = [div.parent for div in soup.select('div > div.row')]
print(divs)
Outputs:
[<div class="consider"><div class="row"><p>Text1</p></div></div>, <div class="Consider"><div class="row"><p>Text2</p></div></div>]

Python: extract all the information(src, href, title) inside the class

I found that I can extract all the information I want from this HTML. I need to extract title, href abd src from this.
HTML:
<div class="col-md-2 col-sm-2 col-xs-2 home-hot-thumb">
<a itemprop="url" href="/slim?p=3090" class="main">
<img src="/FileUploads/Post/3090.jpg?w=70&h=70&mode=crop" alt="apple" title="apple" />
</a>
</div>
<div class="col-md-2 col-sm-2 col-xs-2 home-hot-thumb">
<a itemprop="url" href="/slim?p=3091" class="main">
<img src="/FileUploads/Post/3091.jpg?w=70&h=70&mode=crop" alt="banana" title="banana" />
</a>
</div>
Code:
import requests
from bs4 import BeautifulSoup
res = requests.get('http://www.cad.com/')
soup = BeautifulSoup(res.text,"lxml")
for a in soup.findAll('div', {"id":"home"}):
for b in a.select(".main"):
print ("http://www.cad.com"+b.get('href'))
print(b.get('title'))
I can successfully get href from this, but since title and src are in another line, I don't know how to extract them. After this, I want to save them in excel, so maybe I need to finish one first then do the second one.
Expected output:
/slim?p=3090
apple
/FileUploads/Post/3091.jpg?w=70&h=70&mode=crop" alt="banana" title="banana
/slim?p=3091
banana
/FileUploads/Post/3091.jpg?w=70&h=70&mode=crop" alt="banana" title="banana
My own solution:
import requests
from bs4 import BeautifulSoup
res = requests.get('http://www.cad.com/')
soup = BeautifulSoup(res.text,"lxml")
for a in soup.findAll('div', {"id":"home"}):
div = a.findAll('div', {"class": "home-hot-thumb"})
for div in div:
title=(div.img.get('title'))
print(title)
href=('http://www.cad.com/'+div.a.get('href'))
print(href)
src=('http://www.cad.com/'+div.img.get('src'))
print(src.replace('?w=70&h=70&mode=crop', ''))

Using page text to select `html` element using`Beautiful Soup`

I have a page which contains several repetitions of: <div...><h4>...<p>... For example:
html = '''
<div class="proletariat">
<h4>sickle</h4>
<p>Ignore this text</p>
</div>
<div class="proletariat">
<h4>hammer</h4>
<p>This is the text we want</p>
</div>
'''
from bs4 import BeautifulSoup
soup = BeautifulSoup(html)
If I write print soup.select('div[class^="proletariat"] > h4 ~ p'), I get:
[<p>Ignore this text</p>, <p>This is the text we want</p>]
How do I specify that I only want the text of p when it is preceded by <h4>hammer</h4>?
Thanks
html = '''
<div class="proletariat">
<h4>sickle</h4>
<p>Ignore this text</p>
</div>
<div class="proletariat">
<h4>hammer</h4>
<p>This is the text we want</p>
</div>
'''
import re
from bs4 import BeautifulSoup
soup = BeautifulSoup(html)
print(soup.find("h4", text=re.compile('hammer')).next_sibling.next.text)
This is the text we want
:contains() could help here, but it is not supported.
Taking this into account, you can use select() in conjunction with the find_next_sibling():
print next(h4.find_next_sibling('p').text
for h4 in soup.select('div[class^="proletariat"] > h4')
if h4.text == "hammer")

Categories

Resources