CoCalc -- htmlParsing.py

GitHub Repository: REMitchell/python-crawling
Path: blob/master/1-HTML-Parsing/htmlParsing.py
¹⁶⁴ views

1
from urllib.request import urlopen
2
from bs4 import BeautifulSoup
3

4
html = urlopen("http://www.oreilly.com/")
5
bsObj = BeautifulSoup(html,"lxml")
6
image = bsObj.find("img", {"alt":"O'Reilly Media, Inc."})
7
print(image.attrs['src'])
8