I have a div whose id is "img-cont"
<div class="img-cont-box" id="img-cont" style='background-image: url("http://example.com/example.jpg");'>
I want to extract the url in background-image using beautiful soup.How can I do it?
You can you find_all or find for the first match.
import re
soup = BeautifulSoup(html_str)
result = soup.find('div',attrs={'id':'img-cont','style':True})
if result is not None:
url = re.findall('\("(http.*)"\)',result['style']) # return a list.
Try this:
import re
from bs4 import BeautifulSoup
html = '''\
<div class="img-cont-box" \
id="img-cont" \
style='background-image: url("http://example.com/example.jpg");'>\
'''
soup = BeautifulSoup(html, 'html.parser')
div = soup.find('div', id='img-cont')
print(re.search(r'url\("(.+)"\)', div['style']).group(1))
Related
I used beautiful soup using python to get data from a specific website
but I don't know how to get one of these prices but I want the price in gram (g)
AS shown below this is the HTML codeL:
<div class="promoPrice margBottom7">16,000
L.L./200g<br/><span class="kiloPrice">79,999
L.L./Kg</span></div>
I use this code:
p_price = product.findAll("div{"class":"promoPricemargBottom7"})[0].text
my result was:
16,000 L.L./200g 79,999 L.L./Kg
but i want to have:
16,000 L.L./200g
only
You will need to first decompose the span inside the div element:
from bs4 import BeautifulSoup
h = """
<div class="promoPrice margBottom7">16,000 L.L./200g<br/>
<span class="kiloPrice">79,999 L.L./Kg</span></div>
"""
soup = BeautifulSoup(h, "html.parser")
element = soup.find("div", {'class': 'promoPrice'})
element.span.decompose()
print(element.text)
#16,000 L.L./200g
Try using soup.select_one('div.promoPrice').contents[0]
from bs4 import BeautifulSoup
html = """<div class="promoPrice margBottom7">16,000 L.L./200g<br/>
<span class="kiloPrice">79,999 L.L./Kg</span></div>"""
soup = BeautifulSoup(html, features='html.parser')
# value = soup.select('div.promoPrice > span') # for 79,999 L.L./Kg
value = soup.select_one('div.promoPrice').contents[0]
print(value)
Prints
16,000 L.L./200g
I use beautifulsoup to extract multiple attribute values of class, but ['fa', 'fa-address-book-o'] is not the result I want.
from bs4 import BeautifulSoup
html = "<i class='fa fa-address-book-o' aria-hidden='true'></i>"
soup = BeautifulSoup(html, "lxml")
h2 = soup.select("i")
print(h2[0]['class'])
I want the effect to be as follows:
fa fa-address-book-o
join all the elements in your list, and put a space between them
from bs4 import BeautifulSoup
html = "<i class='fa fa-address-book-o' aria-hidden='true'></i>"
soup = BeautifulSoup(html, "lxml")
h2 = soup.select("i")
print(' '.join(h2[0]['class']))
I try to catch the text of an id with BeautifulSoup. The result should be 30,66.
My actual code print the complete span element:
[<span class="mainValueAmount simpleTextFit" id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldValue">30,66</span>]
How do I get just the value 30,66?
from bs4 import BeautifulSoup
u = '<div class="widgetBox" data-name="pvEnergy"><div class="widgetHead">PV-Energie</div><div class="widgetBody"><div class="mainValue"><span id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldValue" class="mainValueAmount simpleTextFit">30,66</span><span id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldUnit" class="mainValueUnit">kWh</span><br><span id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldPeriodTitle" class="mainValueDescription">Heute</span></div></div><div id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldTotalDiv" class="widgetFooter">Gesamt: <span id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldTotalValue">158,953</span><span id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldTotalUnit">MWh</span></div></div>'
idAktWert = 'ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldValue'
soup = BeautifulSoup(u, "html.parser")
aktWert = soup.select("#" + idAktWert)
print(aktWert)
Thanks for your help!
Use .text
Ex:
from bs4 import BeautifulSoup
u = '<div class="widgetBox" data-name="pvEnergy"><div class="widgetHead">PV-Energie</div><div class="widgetBody"><div class="mainValue"><span id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldValue" class="mainValueAmount simpleTextFit">30,66</span><span id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldUnit" class="mainValueUnit">kWh</span><br><span id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldPeriodTitle" class="mainValueDescription">Heute</span></div></div><div id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldTotalDiv" class="widgetFooter">Gesamt: <span id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldTotalValue">158,953</span><span id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldTotalUnit">MWh</span></div></div>'
idAktWert = 'ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldValue'
soup = BeautifulSoup(u, "html.parser")
aktWert = soup.select("#" + idAktWert)[0] #Note: I have used Index to select the first element in list.
print(aktWert.text)
Output:
30,66
You simply need get_text() for this.
from bs4 import BeautifulSoup
u = '<div class="widgetBox" data-name="pvEnergy"><div class="widgetHead">PV-Energie</div><div class="widgetBody"><div class="mainValue"><span id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldValue" class="mainValueAmount simpleTextFit">30,66</span><span id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldUnit" class="mainValueUnit">kWh</span><br><span id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldPeriodTitle" class="mainValueDescription">Heute</span></div></div><div id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldTotalDiv" class="widgetFooter">Gesamt: <span id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldTotalValue">158,953</span><span id="ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldTotalUnit">MWh</span></div></div>'
idAktWert = 'ctl00_ContentPlaceHolder1_PublicPagePlaceholder1_PageUserControl_ctl00_PublicPageLoadFixPage_energyYieldWidget_energyYieldValue'
soup = BeautifulSoup(u, "html.parser")
aktWert = soup.select("#" + idAktWert)
// since aktWert is an array, we need to get the 1st index
print(aktWert[0].get_text()) // outputs 30,66
How can I properly extract the value of a <span> WITH the <br/> tags?
i.e.
from bs4 import BeautifulSoup
html_text = '<span id="spamANDeggs">This is<br/>what<br/>I want. WITH the <br/> tags.</span>'
soup = BeautifulSoup(html_text)
text_wanted = soup.find('span',{'id':'spamANDeggs'}).GetText(including<br/>...)
You can use decode_contents() method just like this:
from bs4 import BeautifulSoup
html_text = '<span id="spamANDeggs">This is<br/>what<br/>I want. WITH the <br/> tags.</span>'
soup = BeautifulSoup(html_text)
text_wanted = soup.find('span', {'id': 'spamANDeggs'}).decode_contents(formatter="html")
Now text_wanted equals "This is<br/>what<br/>I want. WITH the <br/> tags."
Folks,
Ive managed to get beautifulsoup to scrape a page with the following
html = response.read()
soup = BeautifulSoup(html)
links = soup.findAll('a')
There are several occurrences of
<A href="javascript:Set_Variables('foo1','bar1''')"onmouseover="javascript: return window.status=''">
<A href="javascript:Set_Variables('foo2','bar2''')"onmouseover="javascript: return window.status=''">
How can I iterate through this and get the foo/bar values?
Thanks
You can use regular expressions to extract variables from href attributes:
import re
from bs4 import BeautifulSoup
data = """
<div>
<table>
<A href="javascript:Set_Variables('foo1','bar1''')" onmouseover="javascript: return window.status=''">
<A href="javascript:Set_Variables('foo2','bar2''')" onmouseover="javascript: return window.status=''">
</table>
</div>
"""
soup = BeautifulSoup(data)
pattern = re.compile(r"javascript:Set_Variables\('(\w+)','(\w+)'")
for a in soup('a'):
match = pattern.search(a['href'])
if match:
print match.groups()
Prints:
('foo1', 'bar1')
('foo2', 'bar2')