python:: urllib.request vs requests

 

import shutil
import tempfile
import urllib.request

with urllib.request.urlopen('http://python.org/') as response:
    with tempfile.NamedTemporaryFile(delete=False) as tmp_file:
        shutil.copyfileobj(response, tmp_file)

with open(tmp_file.name) as html:
    pass

 

 

import os
from pathlib import Path
import urllib.request



def get_download_path():
    """Returns the default downloads path for linux or windows"""
    if os.name == 'nt':
        import winreg
        sub_key = r'SOFTWARE\Microsoft\Windows\CurrentVersion\Explorer\Shell Folders'
        downloads_guid = '{374DE290-123F-4565-9164-39C4925E467B}'
        with winreg.OpenKey(winreg.HKEY_CURRENT_USER, sub_key) as key:
            location = winreg.QueryValueEx(key, downloads_guid)[0]
        return location
    else:
        return os.path.join(os.path.expanduser('~'), 'downloads')


# 저장할 csv 주소
list_csv = [
    "https://raw.githubusercontent.com/HyunchanMOON/lessons/master/lessons/gasprices.csv",
    ]


# 다운로드 폴더
# downloads_path = str(pathlib.Path.home() / "Downloads")
downloads_path = get_download_path()
 
 
# 폴더가 존재하지 않는다면 폴더 생성
if not os.path.isdir(downloads_path): 
    os.makedirs(downloads_path)
 
for x in range(len(list_csv)):
    url = list_csv[x]
    filename = url.split("/")[-1]	
    urllib.request.urlretrieve(url, pathlib.PurePath(downloads_path, filename))

 

 

 

 

requests를 더 많이들 사용하는데,

url RESPONSE 200 이 아닐 때 urllib.request는 ERROR 띄워주는 것이 차이 인 듯

import requests
import urllib.request
from bs4 import BeautifulSoup as bs

url = "https://thekkom.github.io/images/yellow_500px.png"
filename = "logo.png"


# urllib use
urllib.request.urlretrieve(url, filename)


# requests use
req = requests.get(url)
print(req)   # Response [200]
print(dir(req))


# req.context / req.html / req.text
with open(filename, 'wb') as f:
    f.write(req.content)
    f.close()
    print("save file")
    


# for html, use beautifulsoup4
req = requests.get(url)
html = req.text
soup = bs(html, 'html.parser')

 

 

 

 

 

 

 

 

 

참고

 

 

https://docs.python.org/3/library/urllib.request.html

urllib.request — Extensible library for opening URLs

 

 

 

https://docs.python.org/3/howto/urllib2.html#urllib-howto

HOWTO Fetch Internet Resources Using The urllib Package

 

 

 

https://moondol-ai.tistory.com/238

파이썬 크롤링 requests vs urllib.request 차이는?

 

 

 

 

 

 

_