Get the latest jetpack plugin
Page content
http://sosa0sa.com:2368/use-jetpack-for-wordpress-5-0/ 의 연장선. Jetpack plugin의 최신 버전을 알아내서 자동으로 해당 바이너리 파일을 다운로드 받아 보자.
몇 가지 module 을 사용하는데 필요한 module은 https://realpython.com/python-web-scraping-practical-introduction/ 을 참고해서 설치
$ python3 -m venv venv
$ . ./venv/bin/activate
$ pip3 install requests BeautifulSoup4
webscrap.py
from requests import get
from requests.exceptions import RequestException
from contextlib import closing
from bs4 import BeautifulSoup
from urllib.request import *
'''
https://realpython.com/python-web-scraping-practical-introduction/
'''
def simple_get(url):
"""
Attempts to get the content at `url` by making an HTTP GET request.
If the content-type of response is some kind of HTML/XML, return the
text content, otherwise return None.
"""
try:
with closing(get(url, stream=True)) as resp:
if is_good_response(resp):
return resp.content
else:
return None
except RequestException as e:
log_error('Error during requests to {0} : {1}'.format(url, str(e)))
return None
def is_good_response(resp):
"""
Returns True if the response seems to be HTML, False otherwise.
"""
content_type = resp.headers['Content-Type'].lower()
return (resp.status_code == 200
and content_type is not None
and content_type.find('html') > -1)
def log_error(e):
"""
It is always a good idea to log errors.
This function just prints them, but you can
make it do anything.
"""
print(e)
def download_file(base_url, filename):
file_url = '%s/%s' %(base_url, filename)
print("Download %s" %(file_url))
try:
from tqdm import tqdm
except:
urlretrieve(file_url, filename)
return
# use tqdm to display the progress but too slow
file_response = get(file_url, stream=True)
with open(filename, 'wb') as handle:
for data in tqdm(file_response.iter_content()):
handle.write(data)
Jetpack plugin 페이지에 있는 버전 정보를 이용해서 플러그인 다운로드 하기 tqdm은 progress를 보여주는 모듈인데 그냥 사용하면 속도가 너무 너무 느리다. 몇 초면 다운 받을 수 있는 파일을 1분에 걸쳐 받는…
get_jetpack.py
from webscrap import *
'''
https://realpython.com/python-web-scraping-practical-introduction/
https://stackoverflow.com/questions/22676/how-do-i-download-a-file-over-http-using-python
'''
if __name__ == '__main__':
jetpack_url='https://wordpress.org/plugins/jetpack/'
jetpack_ver = None
response = simple_get(jetpack_url)
if response is not None:
html = BeautifulSoup(response, 'html.parser')
for i,l1 in enumerate(html.select('li')):
if l1.text.strip().find("Version:") == 0:
jetpack_ver = l1.text.strip().split()[1]
break
if jetpack_ver is not None:
filename = 'jetpack.%s.zip' %jetpack_ver
download_file(jetpack_url, filename)