How to get text from span tag in BeautifulSoup
You could solve this with just a couple lines of gazpacho:
from gazpacho import Soup
html = """\
<div class="systemRequirementsMainBox">
<div class="systemRequirementsRamContent">
<span title="000 Plus Minimum RAM Requirement">1 GB</span> </div>
"""
soup = Soup(html)
soup.find("span", {"title": "Minimum RAM Requirement"}).text
# '1 GB'
You can use a css selector, pulling the span you want using the title text :
soup = BeautifulSoup("""<div class="systemRequirementsMainBox">
<div class="systemRequirementsRamContent">
<span title="000 Plus Minimum RAM Requirement">1 GB</span> </div>""", "xml")
print(soup.select_one("span[title*=RAM]").text)
That finds the span with a title attribute that contains RAM, it is equivalent to saying in python, if "RAM" in span["title"]
.
Or using find with re.compile
import re
print(soup.find("span", title=re.compile("RAM")).text)
To get all the data:
from bs4 import BeautifulSoup
r = requests.get("http://www.game-debate.com/games/index.php?g_id=21580&game=000%20Plus").content
soup = BeautifulSoup(r,"lxml")
cont = soup.select_one("div.systemRequirementsRamContent")
ram = cont.select_one("span")
print(ram["title"], ram.text)
for span in soup.select("div.systemRequirementsSmallerBox.sysReqGameSmallBox span"):
print(span["title"],span.text)
Which will give you:
000 Plus Minimum RAM Requirement 1 GB
000 Plus Minimum Operating System Requirement Win Xp 32
000 Plus Minimum Direct X Requirement DX 9
000 Plus Minimum Hard Disk Drive Space Requirement 500 MB
000 Plus GD Adjusted Operating System Requirement Win Xp 32
000 Plus GD Adjusted Direct X Requirement DX 9
000 Plus GD Adjusted Hard Disk Drive Space Requirement 500 MB
000 Plus Recommended Operating System Requirement Win Xp 32
000 Plus Recommended Hard Disk Drive Space Requirement 500 MB
I tried to extract the text inside all the span tags inside the HTML document using find_all()
function from bs4
(BeautifulSoup):
from bs4 import BeautifulSoup
import requests
url="YOUR_URL_HERE"
response=requests.get(url)
soup=BeautifulSoup(response.content,html5lib)
spans=soup.find_all('span',"ENTER_Css_CLASS_HERE")
for span in spans:
print(span.text)
You can simply use span
tag in BeautifulSoup or you can include other attributes like class
, title
along with the span
tag.
from BeautifulSoup import BeautifulSoup as BSHTML
htmlText = """<div class="systemRequirementsMainBox">
<div class="systemRequirementsRamContent">
<span title="000 Plus Minimum RAM Requirement">1 GB</span> </div>"""
soup = BSHTML(htmlText)
spans = soup.findAll('span')
# spans = soup.findAll('span', attrs = {'class' : 'your-class-name'}) # or span by class name
# spans = soup.findAll('span', attrs = {'title' : '000 Plus Minimum RAM Requirement'}) # or span with a title
for span in spans:
print span.text