Python: Read URL

pip install urllib
pip install requests
pip install BeautifulSoup4

Contoh 1

import requests
from BeautifulSoup import BeautifulSoup

link = "http://www.somesite.com/details.pl?urn=2344"
f = requests.get(link)
print(f.text)

soup = BeautifulSoup(f)
all_text = .join(soup.findAll(text=True))
print(all_text)

Contoh 2

import urllib
from bs4 import BeautifulSoup

url = "http://news.bbc.co.uk/2/hi/health/2284783.stm"
html = urllib.urlopen(url).read()
soup = BeautifulSoup(html)

# kill all script and style elements
for script in soup(["script", "style"]):
    script.extract()    # rip it out

# get text
text = soup.get_text()

# break into lines and remove leading and trailing space on each
lines = (line.strip() for line in text.splitlines())
# break multi-headlines into a line each
chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
# drop blank lines
text = '\n'.join(chunk for chunk in chunks if chunk)
print(text)

Pranala Menarik

• Python