Difference between revisions of "Python: Read URL"

From OnnoWiki
Jump to navigation Jump to search
 
(5 intermediate revisions by the same user not shown)
Line 1: Line 1:
  pip install requests
+
  pip3 install urllib
 +
pip3 install requests
 +
pip3 install BeautifulSoup4
  
 
+
==Contoh 1==
Script
 
  
 
  import requests
 
  import requests
Line 16: Line 17:
  
  
 +
==Contoh 2==
 +
 +
import requests
 +
import urllib.request
 +
from bs4 import BeautifulSoup
 +
 +
import urllib
 +
from bs4 import BeautifulSoup
 +
 +
url = "https://www.industry.co.id/read/49900/dongkrak-penjualan-tam-hadirkan-toyota-driving-experience"
 +
with urllib.request.urlopen(url) as url:
 +
    html = 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==
 
==Pranala Menarik==
  
 
* [[Python]]
 
* [[Python]]

Latest revision as of 16:54, 12 October 2019

pip3 install urllib
pip3 install requests
pip3 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 requests
import urllib.request
from bs4 import BeautifulSoup

import urllib
from bs4 import BeautifulSoup

url = "https://www.industry.co.id/read/49900/dongkrak-penjualan-tam-hadirkan-toyota-driving-experience"
with urllib.request.urlopen(url) as url:
    html = 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