beautifulsoup python find code example
Example 1: beautifulsoup python
import bs4 as bs
import urllib.request
source = urllib.request.urlopen('https://pythonprogramming.net/parsememcparseface/').read()
Example 2: beautifulsoup
>>> from bs4 import BeautifulSoup
>>> soup = BeautifulSoup("<p>Some<b>bad<i>HTML")
>>> print soup.prettify()
<html>
<body>
<p>
Some
<b>
bad
<i>
HTML
</i>
</b>
</p>
</body>
</html>
>>> soup.find(text="bad")
u'bad'
>>> soup.i
<i>HTML</i>
#
>>> soup = BeautifulSoup("<tag1>Some<tag2/>bad<tag3>XML", "xml")
#
>>> print soup.prettify()
<?xml version="1.0" encoding="utf-8">
<tag1>
Some
<tag2 />
bad
<tag3>
XML
</tag3>
</tag1>
Example 3: beautiful soup 4
from bs4 import BeautifulSoup
with open("index.html") as fp:
soup = BeautifulSoup(fp)
soup = BeautifulSoup("<html>a web page</html>")
Example 4: beautifulsoup find
htmlTag = soup.find(id="id")
text = soup.find(id="id").get_text()
Example 5: beautifulsoup find class
mydivs = soup.findAll("div", {"class": "stylelistrow"})
Example 6: python beautifulsoup get attibute
xmlData = None
with open('conf//test1.xml', 'r') as xmlFile:
xmlData = xmlFile.read()
xmlDecoded = xmlData
xmlSoup = BeautifulSoup(xmlData, 'html.parser')
repElemList = xmlSoup.find_all('repeatingelement')
for repElem in repElemList:
print("Processing repElem...")
repElemID = repElem.get('id')
repElemName = repElem.get('name')
print("Attribute id = %s" % repElemID)
print("Attribute name = %s" % repElemName)