You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
107 lines
3.4 KiB
Python
107 lines
3.4 KiB
Python
import os, json, re, shlex
|
|
import subprocess
|
|
from datetime import datetime
|
|
|
|
|
|
def pandoc(pwd, content, format_in, format_out):
|
|
# print('HTML content file:', wiki_content_f.name)
|
|
|
|
# tmp files
|
|
mw_tmp_fn = os.path.join(pwd, '.mediawiki_content')
|
|
html_tmp_fn = os.path.join(pwd, '.html_content') # TODO: join with pw
|
|
for fn in [mw_tmp_fn, html_tmp_fn ]:
|
|
if os.path.isfile(fn) is False:
|
|
os.mknod(fn) # create them if not in dir
|
|
with open(mw_tmp_fn, 'w') as mw_tmp_fn_:
|
|
mw_tmp_fn_.write(content)
|
|
|
|
pandoc_cmd = f"pandoc {mw_tmp_fn} -f {format_in} -t {format_out} -o {html_tmp_fn}"
|
|
subprocess.call(shlex.split(pandoc_cmd))
|
|
|
|
with open(html_tmp_fn, 'r') as html_tmp_fn_:
|
|
output = html_tmp_fn_.read()
|
|
|
|
return output
|
|
|
|
|
|
def page_props(wikicontent):
|
|
exp = re.compile(r'\|(\w*?)\=(.*)', flags=re.M)
|
|
found = re.findall(exp, wikicontent)
|
|
found_dict ={item[0]: item[1] for item in found}
|
|
return found_dict
|
|
|
|
|
|
def unpack_response(response):
|
|
# printout is ordered dict
|
|
d = {}
|
|
printouts = response['printouts']
|
|
page = response['fulltext']
|
|
fullurl = response['fullurl']
|
|
d['page'] = page
|
|
for prop in printouts:
|
|
p_item = response['printouts'][prop]
|
|
for prop_val in p_item:
|
|
if isinstance(prop_val, dict) is False:
|
|
d[prop] = prop_val
|
|
else:
|
|
# if len(prop_val) > 0:
|
|
props = list(prop_val.keys())
|
|
if 'fulltext' in props:
|
|
val = prop_val.get('fulltext')
|
|
elif 'timestamp' in props:
|
|
val = datetime.fromtimestamp(int(prop_val.get('timestamp')))
|
|
else:
|
|
val = list(prop_val.values())[0]
|
|
d[prop] = val
|
|
return page, d, fullurl
|
|
|
|
|
|
def update_json(imgsjson_fn, img_dict, img_fn):
|
|
# write img_dict to json file
|
|
if os.path.isfile(imgsjson_fn) is True: # if json exists
|
|
with open(imgsjson_fn, 'r') as imgsjson_file: # read its content
|
|
imgsjson_dict = json.load(imgsjson_file)
|
|
# print(imgsjson_dict)
|
|
else: # other wise
|
|
imgsjson_dict = {} # imgsjson_dict will be an empty dictionary
|
|
|
|
# is file already in dict
|
|
if img_dict['name'] in imgsjson_dict.keys():
|
|
# check if
|
|
# file is locally stored
|
|
img_issaved = os.path.isfile(img_fn)
|
|
# timestamp in json is same as in img object
|
|
img_samets = imgsjson_dict[img_dict['name']]['timestamp'] == img_dict['timestamp']
|
|
if all([img_issaved, img_samets]) is False: # if one or more is False
|
|
# ask it to download again
|
|
download = True
|
|
imgsjson_dict[img_dict['name']] = img_dict # add img_dict to imgsjson_dict under the key of the img.name
|
|
else:
|
|
download = False
|
|
else:
|
|
download = True
|
|
imgsjson_dict[img_dict['name']] = img_dict # add img_dict to imgsjson_dict under the key of the img.name
|
|
|
|
with open(imgsjson_fn, 'w') as imgsjson_file:
|
|
json.dump(imgsjson_dict, imgsjson_file, indent=4)
|
|
|
|
return download
|
|
|
|
|
|
def clean_dir(dirfullpath):
|
|
for f in os.listdir(dirfullpath):
|
|
f = os.path.join(dirfullpath, f)
|
|
if os.path.isfile(f):
|
|
os.remove(f)
|
|
|
|
|
|
|
|
class Colors:
|
|
HEADER = '\033[95m'
|
|
BLUE = '\033[94m'
|
|
GREEN = '\033[92m'
|
|
WARNING = '\033[93m'
|
|
FAIL = '\033[91m'
|
|
ENDC = '\033[0m'
|
|
BOLD = '\033[1m'
|
|
UNDERLINE = '\033[4m' |