python-libzim

from libzim.reader import Archive
from libzim.search import Query, Searcher
from libzim.suggestion import SuggestionSearcher

zim = Archive("test.zim")
print(f"Main entry is at {zim.main_entry.get_item().path}")
entry = zim.get_entry_by_path("home/fr")
print(f"Entry {entry.title} at {entry.path} is {entry.get_item().size}b.")
print(bytes(entry.get_item().content).decode("UTF-8"))

# searching using full-text index
search_string = "Welcome"
query = Query().set_query(search_string)
searcher = Searcher(zim)  # or Searcher() followed by searcher.add_archive(...)
search = searcher.search(query)
search_count = search.get_estimated_matches()
print(f"there are {search_count} matches for {search_string}")
for result in search.get_results(0, search_count):
    print(result.archive, result.path, result.title, result.snippet)

# accessing suggestions
search_string = "kiwix"
suggestion_searcher = SuggestionSearcher(zim)
suggestion = suggestion_searcher.suggest(search_string)
suggestion_count = suggestion.get_estimated_matches()
print(f"there are {suggestion_count} matches for {search_string}")
print(list(suggestion.get_results(0, suggestion_count)))

import base64
import pathlib

from libzim.writer import Creator, Item, StringProvider, FileProvider, Hint


class MyItem(Item):
    def __init__(self, title, path, content="", fpath=None):
        super().__init__()
        self.path = path
        self.title = title
        self.content = content
        self.fpath = fpath

    def get_path(self):
        return self.path

    def get_title(self):
        return self.title

    def get_mimetype(self):
        return "text/html"

    def get_contentprovider(self):
        if self.fpath is not None:
            return FileProvider(self.fpath)
        return StringProvider(self.content)

    def get_hints(self):
        return {Hint.FRONT_ARTICLE: True}


content = """<html><head><meta charset="UTF-8"><title>Web Page Title</title></head>
<body><h1>Welcome to this ZIM</h1><p>Kiwix</p></body></html>"""

pathlib.Path("home-fr.html").write_text(
    """<html><head><meta charset="UTF-8">
    <title>Bonjour</title></head>
    <body><h1>this is home-fr</h1></body></html>"""
)

item = MyItem("Hello Kiwix", "home", content)
item2 = MyItem("Bonjour Kiwix", "home/fr", None, "home-fr.html")

# illustration = pathlib.Path("icon48x48.png").read_bytes()
illustration = base64.b64decode(
    "iVBORw0KGgoAAAANSUhEUgAAADAAAAAwAQMAAABtzGvEAAAAGXRFWHRTb2Z0d2FyZQBB"
    "ZG9iZSBJbWFnZVJlYWR5ccllPAAAAANQTFRFR3BMgvrS0gAAAAF0Uk5TAEDm2GYAAAAN"
    "SURBVBjTY2AYBdQEAAFQAAGn4toWAAAAAElFTkSuQmCC"
)

with Creator("test.zim").config_indexing(True, "eng") as creator:
    creator.set_mainpath("home")
    creator.add_item(item)
    creator.add_item(item2)
    # square illustration at scale 1
    creator.add_illustration(illustration, 48)
    for name, value in {
        "creator": "python-libzim",
        "description": "Created in python",
        "name": "my-zim",
        "publisher": "You",
        "title": "Test ZIM",
        "language": "eng",
        "date": "2024-06-30",
    }.items():

        creator.add_metadata(name.title(), value)

lock = threading.Lock()
with Creator("test.zim") as creator:

    # Thread #1
    with lock:
        creator.add_item(item1)

    # Thread #2
    with lock:
        creator.add_item(item2)