LICENSE
README.rst
pyproject.toml
docs/source/conf.py
examples/archive_demo.py
examples/archive_functionality_demo.py
examples/final_archive_demo.py
examples/jupyter_demo.py
examples/new_api_demo.py
piedomains/__init__.py
piedomains/api.py
piedomains/archive_org_downloader.py
piedomains/archive_support.py
piedomains/base.py
piedomains/config.py
piedomains/constants.py
piedomains/context_managers.py
piedomains/fetchers.py
piedomains/http_client.py
piedomains/logging.py
piedomains/piedomain.py
piedomains/utils.py
piedomains.egg-info/PKG-INFO
piedomains.egg-info/SOURCES.txt
piedomains.egg-info/dependency_links.txt
piedomains.egg-info/entry_points.txt
piedomains.egg-info/requires.txt
piedomains.egg-info/top_level.txt
piedomains/classifiers/__init__.py
piedomains/classifiers/combined_classifier.py
piedomains/classifiers/image_classifier.py
piedomains/classifiers/text_classifier.py
piedomains/model/calibrate/text/adv.sav
piedomains/model/calibrate/text/alcohol.sav
piedomains/model/calibrate/text/automobile.sav
piedomains/model/calibrate/text/dating.sav
piedomains/model/calibrate/text/downloads.sav
piedomains/model/calibrate/text/drugs.sav
piedomains/model/calibrate/text/education.sav
piedomains/model/calibrate/text/finance.sav
piedomains/model/calibrate/text/fortunetelling.sav
piedomains/model/calibrate/text/forum.sav
piedomains/model/calibrate/text/gamble.sav
piedomains/model/calibrate/text/government.sav
piedomains/model/calibrate/text/hobby.sav
piedomains/model/calibrate/text/hospitals.sav
piedomains/model/calibrate/text/imagehosting.sav
piedomains/model/calibrate/text/isp.sav
piedomains/model/calibrate/text/jobsearch.sav
piedomains/model/calibrate/text/models.sav
piedomains/model/calibrate/text/movies.sav
piedomains/model/calibrate/text/music.sav
piedomains/model/calibrate/text/news.sav
piedomains/model/calibrate/text/politics.sav
piedomains/model/calibrate/text/porn.sav
piedomains/model/calibrate/text/radiotv.sav
piedomains/model/calibrate/text/recreation.sav
piedomains/model/calibrate/text/redirector.sav
piedomains/model/calibrate/text/religion.sav
piedomains/model/calibrate/text/science.sav
piedomains/model/calibrate/text/searchengines.sav
piedomains/model/calibrate/text/sex.sav
piedomains/model/calibrate/text/shopping.sav
piedomains/model/calibrate/text/socialnet.sav
piedomains/model/calibrate/text/spyware.sav
piedomains/model/calibrate/text/tracker.sav
piedomains/model/calibrate/text/urlshortener.sav
piedomains/model/calibrate/text/warez.sav
piedomains/model/calibrate/text/weapons.sav
piedomains/model/calibrate/text/webmail.sav
piedomains/model/calibrate/text/webradio.sav
piedomains/notebooks/01_get_shallalist.ipynb
piedomains/notebooks/01_scrape_webpages.ipynb
piedomains/notebooks/01a_scrape_stratified_random_sample.ipynb
piedomains/notebooks/01b_scraper_webpages_all.ipynb
piedomains/notebooks/01c_upload_to_dataverse.ipynb
piedomains/notebooks/02_parse_html_data.ipynb
piedomains/notebooks/03_data_clean_up.ipynb
piedomains/notebooks/04_train_model.ipynb
piedomains/notebooks/05_text_calibrate_isotonic.ipynb
piedomains/notebooks/06_preprocessing_images.ipynb
piedomains/notebooks/07_train_images.ipynb
piedomains/notebooks/08_yougov_test.ipynb
piedomains/notebooks/archive-upload-screenshot-to-dataverse.ipynb
piedomains/notebooks/chatgpt_baseline.py
piedomains/processors/__init__.py
piedomains/processors/content_processor.py
piedomains/processors/text_processor.py
piedomains/scripts/screenshot.py
piedomains/tests/__init__.py
piedomains/tests/test_001_pred_domain_text.py
piedomains/tests/test_002_pred_domain_images.py
piedomains/tests/test_003_pred_domain_combined.py
piedomains/tests/test_004_domain_validation.py
piedomains/tests/test_005_text_processing.py
piedomains/tests/test_006_error_handling.py
piedomains/tests/test_007_utils.py
piedomains/tests/test_008_config.py
piedomains/tests/test_009_context_managers.py
piedomains/tests/test_010_url_support.py
piedomains/tests/test_011_new_api_integration.py
piedomains/tests/test_012_archive_functionality.py
piedomains/tests/test_013_performance_benchmarks.py
piedomains/tests/test_014_critical_integration.py
streamlit/streamlit_app.py