SGCC 사인머신 (대충짠코드)

everything-to-jpg.bat

 PowerShell.exe -ExecutionPolicy Bypass -File .\everything-to-jpg.ps1

everything-to-jpg.ps1

# https://imagemagick.org/script/download.php#windows
# If a motherhubbard uploaded pdf, also download https://ghostscript.com/releases/gsdnld.html (64bit)

mkdir jpg
Get-ChildItem -File | Foreach {magick convert $_.name ".\\jpg\\$((Get-Item $_.fullname).Basename).jpg"}

get-signs.py

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.firefox.options import Options

import urllib, re, time, os, shutil

signimgpath = os.path.join(
                 os.path.dirname(__file__),
                 "signs")
fallbackdownloadpath = os.path.join(
                 os.path.dirname(__file__),
                 "fdownload")
if not os.path.exists(signimgpath):
    os.mkdir(signimgpath)
if os.path.exists(fallbackdownloadpath):
    shutil.rmtree(fallbackdownloadpath, )
os.mkdir(fallbackdownloadpath)


options = Options()
options.set_preference("browser.download.folderList", 2)
options.set_preference("browser.download.manager.showWhenStarting", False)
options.set_preference("browser.download.dir", fallbackdownloadpath)
options.set_preference("browser.download.useDownloadDir", False)
options.set_preference("browser.helperApps.neverAsk.saveToDisk", "application/x-gzip")

driver = webdriver.Firefox(options=options)
"""
name-link.csv example
<저장할 때 "쉼표로 분리된 파일(.csv) UTF-8 포맷"으로>


갯가재,https://drive.google.com/open?id=somethingsomething

"""
def gen_path(name, ext = None):
    if ext == None:
        ext = re.search(r"-\s+.+(\.\w+)\s+- Google Drive", driver.title).group(1)
    savename = name.strip() + ext
    print(savename)
    savepath = os.path.join(signimgpath, savename)
    return savepath

retry = 10
def download(name):
    element = False
    for i in range(retry):
        try:
            element = driver.find_element(By.XPATH, '//img[starts-with(@src,"https://lh3.googleusercontent.com/drive-viewer/")]')
            img_link = element.get_property("src")
            savepath = gen_path(name)
            urllib.request.urlretrieve(img_link, savepath)
            break
        except:
            pass
        time.sleep(1)
    else: ## Fallback
        savepath = gen_path(name)
        driver.find_element(By.XPATH, "//div[@aria-label='다운로드']").click()
        time.sleep(10)
        print(f"I will kill {name}")
        fname = os.path.join(fallbackdownloadpath, os.listdir(fallbackdownloadpath)[0])
        shutil.move(fname, savepath)
        
f = open("name-link.csv", encoding="utf-8-sig")
for (name, l) in [tuple(line.split(',')) for line in f.readlines()]:
    print(f"name: {name}, l:{l}")
    driver.get(l)
    ##wait
    time.sleep(5)
    download(name.strip())
driver.close()

signs-to-table.py

import docx
from docx.shared import Cm

import os

signimgpath = os.path.join(
                 os.path.dirname(__file__),
                 "signs")

path = os.path.join(signimgpath, "jpg")
doc = os.path.join(signimgpath, "signs.docx")

namef = open("name-link.csv", encoding="utf-8-sig")

d = docx.Document()
names = [i.split(',')[0] for i in namef.readlines()]
l = len(names)
print(f"l = {l}")
t = d.add_table(l, 2)

namef.close()

for (i,name) in enumerate(names):
    """
    CELL 0 : Name (font:Gulim)
    """
    namep = t.cell(i,0).paragraphs[0]
    namer = namep.add_run(name.strip())
    namef = namer.font
    namef.name = "Gulim"
    """
    CELL 1 : Image (height: 1.6cm)
    """
    c = t.cell(i,1)
    p = c.paragraphs[0]
    r = p.add_run()
    iname = os.path.join(path , name.strip() + ".jpg")
    print(f"name = {iname}")
    r.add_picture(iname,height=Cm(1.6))


d.save(doc)

pip install selenium
pip install python-docx

.ps1 스크립트는 imagemagick 필요

get-signs.py -> everything-to-jpg.bat -> signs-to-table.py

순서대로 하면 되고 결과물은 ./signs/signs.docx 로 나온다