Get a Python web page, character encode it, and display it

import requests

# GET
r = requests.get(URL)
#GET parameter
r = requests.get(URL, params={'key': 'val'})

# POST
p = requests.post(URL, data={'key': 'val'})

#Basic authentication
b = requests.get(URL, auth=('User ID', 'password'))

import sys
import requests

url = sys.argv[1]
r = requests.get(url)
#r.json()You can also get it with json

r.encoding = r.apparent_encoding
print(r.text)

import sys
import re
import requests

url = sys.argv[1]
r = requests.get(url)

#Assuming the charset is at the beginning, only the beginning is decoded as an ASCII string
scanned_text = r.content[:1024].decode('ascii', errors='replace')

#Extract the charset value with a regular expression from the decoded string
match = re.search(r'charset=["\']?([\w-]+)', scanned_text)
if match:
    r.encoding = match.group(1)
else:
    r.encoding = 'utf-8'

print(r.text)

Recommended Posts