Index

_

__getattr__() (in module piedomains) __init__() (piedomains.api.DomainClassifier method) (piedomains.config.Config method) (piedomains.context_managers.ResourceManager method) (piedomains.fetchers.ArchiveFetcher method) (piedomains.fetchers.BaseFetcher method) (piedomains.fetchers.FetchResult method) (piedomains.fetchers.PlaywrightFetcher method) (piedomains.http_client.PooledHTTPClient method) (piedomains.image.ImageClassifier method) (piedomains.llm.config.LLMConfig method) (piedomains.llm.LLMConfig method), [1] (piedomains.text.TextClassifier method)

__init_subclass__() (piedomains.base.Base class method) __post_init__() (piedomains.llm.config.LLMConfig method) (piedomains.llm.LLMConfig method), [1]

A

add_driver() (piedomains.context_managers.ResourceManager method) add_fetcher() (piedomains.context_managers.ResourceManager method) add_temp_directory() (piedomains.context_managers.ResourceManager method) add_temp_file() (piedomains.context_managers.ResourceManager method)

allowed_content_types (piedomains.config.Config property) api_key (piedomains.llm.config.LLMConfig attribute), [1] (piedomains.llm.LLMConfig attribute), [1], [2], [3] ArchiveFetcher (class in piedomains.fetchers)

B

Base (class in piedomains.base) base_url (piedomains.llm.config.LLMConfig attribute), [1] (piedomains.llm.LLMConfig attribute), [1], [2], [3]

BaseFetcher (class in piedomains.fetchers) batch_progress_tracking() (in module piedomains.context_managers) batch_size (piedomains.config.Config property) blocked_extensions (piedomains.config.Config property)

C

categories (piedomains.llm.config.LLMConfig attribute), [1] (piedomains.llm.LLMConfig attribute), [1], [2], [3] classes (in module piedomains.constants) classify() (piedomains.api.DomainClassifier method) (piedomains.image.ImageClassifier method) (piedomains.text.TextClassifier method) classify_by_images() (piedomains.api.DomainClassifier method) classify_by_llm() (piedomains.api.DomainClassifier method) classify_by_llm_multimodal() (piedomains.api.DomainClassifier method) classify_by_text() (piedomains.api.DomainClassifier method) classify_domains() (in module piedomains.api) classify_from_collection() (piedomains.api.DomainClassifier method) classify_from_data() (piedomains.image.ImageClassifier method) (piedomains.text.TextClassifier method)

classify_from_paths() (piedomains.image.ImageClassifier method) (piedomains.text.TextClassifier method) cleanup_all() (piedomains.context_managers.ResourceManager method) close() (piedomains.http_client.PooledHTTPClient method) close_global_client() (in module piedomains.http_client) collect_content() (piedomains.api.DomainClassifier method) Config (class in piedomains.config) configure() (in module piedomains.config) configure_llm() (piedomains.api.DomainClassifier method) content_length_limits (piedomains.config.Config property) content_safety_mode (piedomains.config.Config property) cost_limit_usd (piedomains.llm.config.LLMConfig attribute), [1] (piedomains.llm.LLMConfig attribute), [1], [2], [3]

D

data_cleanup() (piedomains.piedomain.Piedomain class method) DEFAULT_CONFIG (piedomains.config.Config attribute)

DomainClassifier (class in piedomains.api) download_file() (in module piedomains.utils) download_from_archive_org() (in module piedomains.archive_org_downloader)

E

enable_content_validation (piedomains.config.Config property) error (piedomains.fetchers.FetchResult attribute) error_recovery() (in module piedomains.context_managers)

extract_html_text() (piedomains.piedomain.Piedomain class method) extract_htmls() (piedomains.piedomain.Piedomain class method) extract_image_tensor() (piedomains.piedomain.Piedomain class method) extract_images() (piedomains.piedomain.Piedomain class method)

F

fetch_batch() (piedomains.fetchers.ArchiveFetcher method) (piedomains.fetchers.PlaywrightFetcher method) fetch_both() (piedomains.fetchers.PlaywrightFetcher method) fetch_content() (piedomains.fetchers.PlaywrightFetcher method) fetch_html() (piedomains.fetchers.ArchiveFetcher method) (piedomains.fetchers.PlaywrightFetcher method) fetch_screenshot() (piedomains.fetchers.ArchiveFetcher method) (piedomains.fetchers.PlaywrightFetcher method)

fetch_single() (piedomains.fetchers.ArchiveFetcher method) (piedomains.fetchers.PlaywrightFetcher method) FetchResult (class in piedomains.fetchers) file_cleanup() (in module piedomains.context_managers) from_dict() (piedomains.llm.config.LLMConfig class method) (piedomains.llm.LLMConfig class method), [1]

G

get() (piedomains.config.Config method) (piedomains.http_client.PooledHTTPClient method) get_batch_prompt() (in module piedomains.llm.prompts) get_category_count() (in module piedomains.constants) get_classification_prompt() (in module piedomains.llm), [1] (in module piedomains.llm.prompts) get_closest_snapshot() (in module piedomains.archive_org_downloader) get_config() (in module piedomains.config) get_custom_prompt() (in module piedomains.llm.prompts)

get_driver() (piedomains.piedomain.Piedomain class method) get_fetcher() (in module piedomains.fetchers) get_file_hash() (in module piedomains.utils) get_http_client() (in module piedomains.http_client) get_llm_usage_stats() (piedomains.api.DomainClassifier method) get_model_info() (piedomains.base.Base class method) get_multimodal_prompt() (in module piedomains.llm), [1] (in module piedomains.llm.prompts) get_urls_year() (in module piedomains.archive_org_downloader) get_valid_categories() (in module piedomains.constants)

H

html (piedomains.fetchers.FetchResult attribute)

http_client() (in module piedomains.http_client) http_timeout (piedomains.config.Config property)

I

image_size (piedomains.config.Config property) ImageClassifier (class in piedomains.image) img_height (piedomains.piedomain.Piedomain attribute)

img_width (piedomains.piedomain.Piedomain attribute) is_valid_category() (in module piedomains.constants) is_within_directory() (in module piedomains.utils)

L

LLMConfig (class in piedomains.llm), [1] (class in piedomains.llm.config) load_model() (piedomains.piedomain.Piedomain class method)

load_model_data() (piedomains.base.Base class method) load_models() (piedomains.image.ImageClassifier method) (piedomains.text.TextClassifier method)

M

max_content_length (piedomains.config.Config property) max_retries (piedomains.config.Config property) max_tokens (piedomains.llm.config.LLMConfig attribute), [1] (piedomains.llm.LLMConfig attribute), [1], [2], [3] meta_description (piedomains.fetchers.FetchResult attribute) model (piedomains.llm.config.LLMConfig attribute), [1] (piedomains.llm.LLMConfig attribute), [1], [2], [3] model_file_name (piedomains.image.ImageClassifier attribute) (piedomains.piedomain.Piedomain attribute) (piedomains.text.TextClassifier attribute) MODELFN (piedomains.base.Base attribute) (piedomains.image.ImageClassifier attribute) (piedomains.piedomain.Piedomain attribute) (piedomains.text.TextClassifier attribute) module piedomains piedomains.api piedomains.archive_org_downloader piedomains.base piedomains.config piedomains.constants piedomains.context_managers piedomains.fetchers piedomains.http_client piedomains.image piedomains.llm, [1] piedomains.llm.config piedomains.llm.prompts piedomains.llm.response_parser piedomains.piedomain piedomains.text piedomains.utils

most_common_words (in module piedomains.constants)

P

page_load_timeout (piedomains.config.Config property) parallel_workers (piedomains.config.Config property) parse_batch_response() (in module piedomains.llm.response_parser) parse_llm_response() (in module piedomains.llm), [1] (in module piedomains.llm.response_parser) parse_url_to_domain() (piedomains.piedomain.Piedomain static method) Piedomain (class in piedomains.piedomain) piedomains module piedomains.api module piedomains.archive_org_downloader module piedomains.base module piedomains.config module piedomains.constants module piedomains.context_managers module piedomains.fetchers module

piedomains.http_client module piedomains.image module piedomains.llm module, [1] piedomains.llm.config module piedomains.llm.prompts module piedomains.llm.response_parser module piedomains.piedomain module piedomains.text module piedomains.utils module playwright_context() (in module piedomains.context_managers) PlaywrightFetcher (class in piedomains.fetchers) PooledHTTPClient (class in piedomains.http_client) provider (piedomains.llm.config.LLMConfig attribute), [1] (piedomains.llm.LLMConfig attribute), [1], [2], [3]

R

REPO_BASE_URL (in module piedomains.utils)

ResourceManager (class in piedomains.context_managers) retry_delay (piedomains.config.Config property)

S

safe_extract() (in module piedomains.utils) sandbox_mode_required (piedomains.config.Config property) save_image() (piedomains.piedomain.Piedomain class method) screenshot_path (piedomains.fetchers.FetchResult attribute) screenshot_wait_time (piedomains.config.Config property)

SecurityError session (piedomains.http_client.PooledHTTPClient property) set() (piedomains.config.Config method) set_config() (in module piedomains.config) success (piedomains.fetchers.FetchResult attribute) suspicious_url_patterns (piedomains.config.Config property)

T

temperature (piedomains.llm.config.LLMConfig attribute), [1] (piedomains.llm.LLMConfig attribute), [1], [2], [3] temporary_directory() (in module piedomains.context_managers) text (piedomains.fetchers.FetchResult attribute) text_from_html() (piedomains.piedomain.Piedomain class method)

TextClassifier (class in piedomains.text) title (piedomains.fetchers.FetchResult attribute) to_dict() (piedomains.config.Config method) to_litellm_params() (piedomains.llm.config.LLMConfig method) (piedomains.llm.LLMConfig method), [1]

U

update() (piedomains.config.Config method) url (piedomains.fetchers.FetchResult attribute)

usage_tracking (piedomains.llm.config.LLMConfig attribute), [1] (piedomains.llm.LLMConfig attribute), [1], [2], [3] user_agent (piedomains.config.Config property)

V

validate_domain_name() (piedomains.piedomain.Piedomain static method) validate_domains() (piedomains.piedomain.Piedomain class method)

validate_input() (piedomains.piedomain.Piedomain class method) validate_url_or_domain() (piedomains.piedomain.Piedomain static method) validate_urls_or_domains() (piedomains.piedomain.Piedomain class method)

W

webdriver_context() (in module piedomains.context_managers) webdriver_timeout (piedomains.config.Config property)

webdriver_window_size (piedomains.config.Config property) weights_loaded (piedomains.piedomain.Piedomain attribute)