darktable_to_lightgallery/create_gallery_search.py

#!/usr/bin/python3
#coding: utf-8

import json
import logging
import os
from os import listdir
from os.path import isdir, isfile, join
import re
from string import Template
import sys
import traceback
from optparse import OptionParser

__all__ = []
__version__ = '0.1'
__date__ = '2021-12-27'
__updated__ = '2021-12-27'

DEBUG = 1
TESTRUN = 0
PROFILE = 0

def collect_tagged_images(searchindex, d, tagnr, image_metadata):
    title = ''
    with open(join(d, 'index.html'), mode="r") as file:
        logging.info(join(d, 'index.html'))
        for line in file:
            titlematch = re.search("h1>(.+?)<", line)
            if titlematch:
                title = titlematch.group(1)
                # print(title)
                y = re.search("\d\d\d\d\s+(\D.*)", title)
                if y:
                    title = y.group(1)
                    #print(title)
                found = next((i for i, item in enumerate(searchindex) if
                          (item["name"] == title) and item["type"] == 'gallery'), None)
                if found:
                    pass
                else:
                    searchindex.append({'id':tagnr, 'name':title, 'type':'gallery', 'dir':d})
                    tagnr = tagnr + 1
            z = re.search('href=[\'"](.*?)["\'].*data_index=["\'](.+?)["\']>', line)
            alltags = ''
            if z:
                img, data = z.groups()
                data = data.replace("'","")
                tags = data.split(',')
                if len(tags) == 0:
                    tags = data
                for t in tags:
                    [typus,val] = t.split('|')
                    alltags = alltags + ', ' + val
                    found = next((i for i, item in enumerate(searchindex) if
                                  (item["name"] == val) and item["type"] == typus), None)
                    if found:
                        searchindex[found]['images'].append(d + '/' + img)
                    else:
                        searchindex.append({'id':tagnr,'name':val,'type':typus,'images':[d + '/' + img]})
                        tagnr = tagnr + 1
                image_metadata[d + '/' + img] = remove_prefix(alltags, ', ')
    return(searchindex, tagnr, image_metadata)
#    return ['','']

def remove_prefix(text, prefix):
    return text[text.startswith(prefix) and len(prefix):]

def get_directories_in_gallerydir(gallerydir):
    onlydirs = []
    for f in listdir(gallerydir):
        if isdir(join(gallerydir, f)):
            if str(f) != '_thumbnails':
                onlydirs.append(f)
    onlydirs.sort()
    return(onlydirs)
                
def create_search_index(gallerydir, opts):
    startdir = os.getcwd()
    os.chdir(gallerydir)
    print('> ' + gallerydir)
    logging.info(f"Creating search index in {gallerydir}")
    dirs = get_directories_in_gallerydir(gallerydir)
    logging.info(dirs)
    searchindex = []
    image_metadata = {}
    i = 0
    tagnr = 0
    for d in dirs:
        print('>> ' + d)
        print('>>> ' + join(d, 'index.html'))
        if not os.path.isfile(join(d, 'index.html')):
            continue;
        print('>>>> ' + d)
        searchindex, tagnr, image_metadata = collect_tagged_images(searchindex, d, tagnr, image_metadata)
        if i == int(opts.limit) - 1:
            print('limit reached')
            break
        i = i + 1
        pass
    # print(json.dumps(searchindex, ensure_ascii=False))
    with open(join(gallerydir, 'searchdata.js'), 'w') as f:
         f.write("var data = '" + json.dumps(searchindex, ensure_ascii=False) + "';\n")
         f.write("var metadata = '" + json.dumps(image_metadata, ensure_ascii=False) + "';\n")
    os.chdir(startdir)

def main(argv=None):
    '''Command line options.'''

    program_name = os.path.basename(sys.argv[0])
    program_version = "v0.1"
    program_build_date = "%s" % __updated__

    program_version_string = '%%prog %s (%s)' % (program_version, program_build_date)
    #program_usage = '''usage: spam two eggs''' # optional - will be autogenerated by optparse
    program_longdesc = '''create index for directory of lightgallery galleries''' # optional - give further explanation about what the program does
    program_license = "Copyright 2021 Markus Spring (markus-spring.info).                                      \
    Licensed under the Apache License 2.0\nhttp://www.apache.org/licenses/LICENSE-2.0"

    if argv is None:
        argv = sys.argv[1:]
    try:
        # setup option parser
        parser = OptionParser(version=program_version_string, epilog=program_longdesc, description=program_license)
        # parser.add_option("-i", "--in", dest="infile", help="set input path [default: %default]", metavar="FILE")
        # parser.add_option("-o", "--out", dest="outfile", help="set output path [default: %default]", metavar="FILE")
        parser.add_option("-l", "--limit", dest="limit", action="store", help="limit number of searched dirs [default: %default]")
        parser.add_option("-v", "--verbose", dest="verbose", action="count", help="set verbosity level [default: %default]")
        parser.add_option("-t", "--title", action="store", dest="title", help="set index title [default: %default]")
        parser.add_option("-w", "--webrootdir", action="store", dest="webrootdir", help="webserver root dir [default: %default]")

        parser.set_defaults( verbose=0, title='sowosamma', webrootdir='/media/thinc_webserver_data', limit=9999)

        (opts, args) = parser.parse_args(argv)

        if len(args) < 1:
            parser.error("directory argument missing")
            
        # MAIN BODY #
        logging.basicConfig(filename=os.path.basename(sys.argv[0]) + '.log', level=logging.INFO)
        create_search_index(args[0], opts)

    except BaseException as ex:
        ex_type, ex_value, ex_traceback = sys.exc_info()         # Get current system exception
        trace_back = traceback.extract_tb(ex_traceback)          # Extract unformatter stack traces as tuples
        stack_trace = list()                                     # Format stacktrace

        for trace in trace_back:
            stack_trace.append("File : %s , Line : %d, Func.Name : %s, Message : %s" % (trace[0], trace[1], trace[2], trace[3]))
        print("Exception type : %s " % ex_type.__name__)
        print("Exception message : %s" %ex_value)
        print("Stack trace : %s" %stack_trace)


if __name__ == "__main__":
    if DEBUG:
        sys.argv.append("-v")
    if TESTRUN:
        import doctest
        doctest.testmod()
    if PROFILE:
        import cProfile
        import pstats
        profile_filename = 'config_reader.config_reader_profile.txt'
        cProfile.run('main()', profile_filename)
        statsfile = open("profile_stats.txt", "wb")
        p = pstats.Stats(profile_filename, stream=statsfile)
        stats = p.strip_dirs().sort_stats('cumulative')
        stats.print_stats()
        statsfile.close()
        sys.exit(0)
    sys.exit(main())


#Local Variables:
#compile-command: "./create_gallery_search.py -l 5 /media/thinc_webserver_data/vaters_dias/"
#End: