epstein-files 1.0.7__py3-none-any.whl → 1.0.9__py3-none-any.whl

epstein_files/documents/email.py

@@ -38,7 +38,6 @@ TIMESTAMP_LINE_REGEX = re.compile(r"\d+:\d+")
 
 SUPPRESS_LOGS_FOR_AUTHORS = ['Undisclosed recipients:', 'undisclosed-recipients:', 'Multiple Senders Multiple Senders']
 REWRITTEN_HEADER_MSG = "(janky OCR header fields were prettified, check source if something seems off)"
-IS_JUNK_MAIL = 'is_junk_mail'
 MAX_CHARS_TO_PRINT = 4000
 MAX_NUM_HEADER_LINES = 14
 MAX_QUOTED_REPLIES = 2
@@ -289,9 +288,10 @@ SELF_EMAILS_FILE_IDS = [
 ]
 
 METADATA_FIELDS = [
-    IS_JUNK_MAIL,
+    'is_junk_mail',
     'recipients',
     'sent_from_device',
+    'subject',
 ]
 
 
@@ -352,7 +352,8 @@ class Email(Communication):
 
     def metadata(self) -> Metadata:
         local_metadata = asdict(self)
-        local_metadata[IS_JUNK_MAIL] = self.is_junk_mail()
+        local_metadata['is_junk_mail'] = self.is_junk_mail()
+        local_metadata['subject'] = self.subject() or None
         metadata = super().metadata()
         metadata.update({k: v for k, v in local_metadata.items() if v and k in METADATA_FIELDS})
         return metadata

epstein_files/util/constant/names.py

@@ -205,12 +205,12 @@ NAMES_TO_NOT_HIGHLIGHT: list[str] = [name.lower() for name in [
     'Carolyn', 'Chris', 'Christina',
     'Dan', 'Daniel', 'Danny', 'Darren', 'Dave', 'David',
     'Ed', 'Edward', 'Edwards', 'Epstein', 'Eric', 'Erika', 'Etienne',
-    'Faith', 'Fred', 'Frost', 'Fuller',
+    'Faith', 'Fred', 'Friendly', 'Frost', 'Fuller',
     'George',
     'Heather', 'Henry', 'Hill', 'Hoffman',
     'Ian',
     'Jack', 'James', 'Jay', 'Jean', 'Jeff', 'Jeffrey', 'Jennifer', 'Jeremy', 'jessica', 'Joel', 'John', 'Jon', 'Jonathan', 'Joseph', 'Jr',
-    'Kahn', 'Katherine', 'Ken', 'Kevin',
+    'Kahn', 'Katherine', 'Kelly', 'Ken', 'Kevin',
     'Larry', 'Leon', 'Lesley', 'Linda', 'Link', 'Lisa',
     'Mann', 'Marc', 'Marie', 'Mark', 'Martin', 'Melanie', 'Michael', 'Mike', 'Miller', 'Mitchell', 'Miles', 'Morris', 'Moskowitz',
     'Nancy', 'Neal', 'New',

epstein_files/util/env.py

@@ -4,42 +4,44 @@ from os import environ
 from pathlib import Path
 from sys import argv
 
-from epstein_files.util.logging import datefinder_logger, env_log_level, logger
+from rich_argparse_plus import RichHelpFormatterPlus
+
+from epstein_files.util.logging import env_log_level, logger
 
 COUNT_WORDS_SCRIPT = 'epstein_word_count'
 DEFAULT_WIDTH = 145
 HTML_SCRIPTS = ['epstein_generate', COUNT_WORDS_SCRIPT]
 
-
-parser = ArgumentParser(description="Parse epstein OCR docs and generate HTML page.")
+RichHelpFormatterPlus.choose_theme('morning_glory')
+parser = ArgumentParser(description="Parse epstein OCR docs and generate HTML pages.", formatter_class=RichHelpFormatterPlus)
 parser.add_argument('--name', '-n', action='append', dest='names', help='specify the name(s) whose communications should be output')
 parser.add_argument('--overwrite-pickle', '-op', action='store_true', help='ovewrite cached EpsteinFiles')
 
 output = parser.add_argument_group('OUTPUT')
 output.add_argument('--all-emails', '-ae', action='store_true', help='all the emails instead of just the interesting ones')
 output.add_argument('--all-other-files', '-ao', action='store_true', help='all the non-email, non-text msg files instead of just the interesting ones')
-output.add_argument('--build', '-b', action='store_true', help='write output to HTML file')
+output.add_argument('--build', '-b', action='store_true', help='write output to an HTML file')
+output.add_argument('--json-metadata', '-jm', action='store_true', help='dump JSON metadata for all files and exit')
 output.add_argument('--make-clean', action='store_true', help='delete all HTML build artifact and write latest URLs to .urls.env')
 output.add_argument('--output-emails', '-oe', action='store_true', help='generate other files section')
-output.add_argument('--output-json-files', action='store_true', help='pretty print all the raw JSON data files in the collection')
+output.add_argument('--output-json-files', action='store_true', help='pretty print all the raw JSON data files in the collection and exit')
 output.add_argument('--output-other-files', '-oo', action='store_true', help='generate other files section')
-output.add_argument('--output-texts', '-ot', action='store_true', help='generate other files section')
+output.add_argument('--output-texts', '-ot', action='store_true', help='generate text messages section')
+output.add_argument('--sort-alphabetical', action='store_true', help='sort emailers alphabetically intead of by email count')
 output.add_argument('--suppress-output', action='store_true', help='no output to terminal (use with --build)')
 output.add_argument('--width', '-w', type=int, default=DEFAULT_WIDTH, help='screen width to use (in characters)')
 output.add_argument('--use-epstein-web-links', action='store_true', help='use epsteinweb.org links instead of epstein.media')
 
 scripts = parser.add_argument_group('SCRIPTS', 'Arguments used only by epstein_search, epstein_show, epstein_diff')
 scripts.add_argument('positional_args', nargs='*', help='strings to searchs for, file IDs to show or diff, etc.')
-scripts.add_argument('--raw', '-r', action='store_true', help='show raw contents of file (only used by scripts)')
-scripts.add_argument('--whole-file', '-wf', action='store_true', help='print whole file (only used by epstein_search)')
+scripts.add_argument('--raw', '-r', action='store_true', help='show raw contents of file (used by epstein_show)')
+scripts.add_argument('--whole-file', '-wf', action='store_true', help='print whole file (used by epstein_search)')
 
 debug = parser.add_argument_group('DEBUG')
 debug.add_argument('--colors-only', '-c', action='store_true', help='print header with color key table and links and exit')
 debug.add_argument('--debug', '-d', action='store_true', help='set debug level to INFO')
 debug.add_argument('--deep-debug', '-dd', action='store_true', help='set debug level to DEBUG')
-debug.add_argument('--json-metadata', '-jm', action='store_true', help='dump JSON metadata for all files')
-debug.add_argument('--json-stats', '-j', action='store_true', help='print JSON formatted stats at the end')
-debug.add_argument('--sort-alphabetical', action='store_true', help='sort emailers alphabetically in counts table')
+debug.add_argument('--json-stats', '-j', action='store_true', help='print JSON formatted stats about the files')
 debug.add_argument('--suppress-logs', '-sl', action='store_true', help='set debug level to FATAL')
 args = parser.parse_args()
 
@@ -52,6 +54,8 @@ args.output_emails = args.output_emails or args.all_emails
 args.output_other_files = args.output_other_files or args.all_other_files
 args.overwrite_pickle = args.overwrite_pickle or (is_env_var_set('OVERWRITE_PICKLE') and not is_env_var_set('PICKLED'))
 args.width = args.width if is_html_script else None
+is_output_selected = any([arg.startswith('output_') and value for arg, value in vars(args).items()])
+is_output_selected = is_output_selected or args.json_metadata or args.colors_only
 specified_names: list[str | None] = [None if n == 'None' else n for n in (args.names or [])]
 
 
@@ -66,14 +70,10 @@ elif not env_log_level:
     logger.setLevel(logging.WARNING)
 
 logger.info(f'Log level set to {logger.level}...')
-datefinder_logger.setLevel(logger.level)
-
 
 # Massage args that depend on other args to the appropriate state
-if not (args.json_metadata or args.output_texts or args.output_emails or args.output_other_files):
-    if is_html_script and current_script != COUNT_WORDS_SCRIPT and not args.make_clean and not args.colors_only:
-        logger.warning(f"No output section chosen; outputting default selection of texts, selected emails, and other files...")
-
+if current_script == 'epstein_generate' and not (is_output_selected or args.make_clean):
+    logger.warning(f"No output section chosen; outputting default selection of texts, selected emails, and other files...")
     args.output_texts = True
     args.output_emails = True
     args.output_other_files = True
@@ -82,4 +82,4 @@ if args.use_epstein_web_links:
     logger.warning(f"Using links to epsteinweb.org links instead of epsteinify.com...")
 
 if args.debug:
-    logger.warning(f"Invocation args:\ncurrent_script={current_script}\nis_html_script={is_html_script},\nspecified_names={specified_names},\nargs={args}")
+    logger.warning(f"Invocation args:\ncurrent_script={current_script}\nis_html_script={is_html_script},\nis_output_selected={is_output_selected}\nspecified_names={specified_names},\nargs={args}")

epstein_files/util/logging.py

@@ -2,6 +2,8 @@ import logging
 from os import environ
 from pathlib import Path
 
+import datefinder
+import rich_argparse_plus
 from rich.console import Console
 from rich.highlighter import ReprHighlighter
 from rich.logging import RichHandler
@@ -43,8 +45,9 @@ logging.basicConfig(level="NOTSET", format="%(message)s", datefmt="[%X]", handle
 logger = logging.getLogger("rich")
 
 
-# Log levels
-datefinder_logger = logging.getLogger('datefinder')  # Set log level to suppress annoying output
+# Set log levels to suppress annoying output
+logging.getLogger('datefinder').setLevel(logging.FATAL)
+logging.getLogger('rich_argparse').setLevel(logging.FATAL)
 env_log_level_str = environ.get(LOG_LEVEL_ENV_VAR) or None
 env_log_level = None
 
@@ -57,7 +60,6 @@ if env_log_level_str:
 
     logger.warning(f"Setting log level to {env_log_level} based on {LOG_LEVEL_ENV_VAR} env var...")
     logger.setLevel(env_log_level)
-    datefinder_logger.setLevel(env_log_level)
 
 
 def log_file_write(file_path: str | Path) -> None:

epstein_files/util/output.py

@@ -105,7 +105,9 @@ def print_emails(epstein_files: EpsteinFiles) -> int:
     if args.all_emails:
         _verify_all_emails_were_printed(epstein_files, already_printed_emails)
 
-    logger.warning(f"Rewrote {len(Email.rewritten_header_ids)} headers of {len(epstein_files.emails)} emails")
+    fwded_articles = [e for e in already_printed_emails if e.config and e.config.is_fwded_article]
+    logger.warning(f"{len(fwded_articles)} of {len(already_printed_emails)} emails were forwarded articles.")
+    logger.warning(f"Rewrote {len(Email.rewritten_header_ids)} headers of {len(epstein_files.emails)} emails.")
     return len(already_printed_emails)
 
 

{epstein_files-1.0.7.dist-info → epstein_files-1.0.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: epstein-files
-Version: 1.0.7
+Version: 1.0.9
 Summary: Tools for working with the Jeffrey Epstein documents released in November 2025.
 Home-page: https://michelcrypt4d4mus.github.io/epstein_text_messages/
 License: GPL-3.0-or-later
@@ -23,6 +23,7 @@ Requires-Dist: python-dateutil (>=2.9.0.post0,<3.0.0)
 Requires-Dist: python-dotenv (>=1.2.1,<2.0.0)
 Requires-Dist: requests (>=2.32.5,<3.0.0)
 Requires-Dist: rich (>=14.2.0,<15.0.0)
+Requires-Dist: rich-argparse-plus (>=0.3.1.4,<0.4.0.0)
 Project-URL: Emails, https://michelcrypt4d4mus.github.io/epstein_text_messages/all_emails_epstein_files_nov_2025.html
 Project-URL: Metadata, https://michelcrypt4d4mus.github.io/epstein_text_messages/file_metadata_epstein_files_nov_2025.json
 Project-URL: Repository, https://github.com/michelcrypt4d4mus/epstein_text_messages
@@ -34,17 +35,18 @@ Description-Content-Type: text/markdown
 
 ![joi](https://github.com/michelcrypt4d4mus/epstein_text_messages/raw/master/docs/joi_ito_gavin_is_clever_epstein_funds_bitcoin_dev_team.png)
 
-* [I Made Epstein's Text Messages Great Again (And You Should Read Them)](https://cryptadamus.substack.com/p/i-made-epsteins-text-messages-great) post on [Substack](https://cryptadamus.substack.com/p/i-made-epsteins-text-messages-great)
-* The Epstein text messages (and some of the emails along with summary information) generated by this code can be viewed [here](https://michelcrypt4d4mus.github.io/epstein_text_messages/).
+* The Epstein text messages (and selected emails and other files) generated by this code can be viewed [here](https://michelcrypt4d4mus.github.io/epstein_text_messages/).
 * All of His Emails along with descriptions of the 496 files that were neither emails nor text messages can be read at [another page also generated by this code](https://michelcrypt4d4mus.github.io/epstein_text_messages/all_emails_epstein_files_nov_2025.html).
-* Word counts for the communications are [here](https://michelcrypt4d4mus.github.io/epstein_text_messages/communication_word_count_epstein_files_nov_2025.html).
+* [Word counts for all of the communications](https://michelcrypt4d4mus.github.io/epstein_text_messages/communication_word_count_epstein_files_nov_2025.html).
 * Metadata containing what I have figured out about who sent or received the communications in a given file (and a brief explanation for how I figured it out for each file) is deployed [here](https://michelcrypt4d4mus.github.io/epstein_text_messages/file_metadata_epstein_files_nov_2025.json)
-* Configuration variables assigning specific `HOUSE_OVERSIGHT_XXXXXX.txt` file IDs (the `111111` part) as being emails to or from particular people based on various research and contributions can be found in [constants.py](./epstein_files/util/constants.py). Everything in `constants.py` appears in the JSON metadata linked above.
+* [I Made Epstein's Text Messages Great Again (And You Should Read Them)](https://cryptadamus.substack.com/p/i-made-epsteins-text-messages-great) post on [Substack](https://cryptadamus.substack.com/p/i-made-epsteins-text-messages-great)
 
 
 ## Usage
-1. Requires you have a local copy of the OCR text files from the House Oversight document release in a directory `/path/to/epstein/ocr_txt_files`. You can download those OCR text files from [the Congressional Google Drive folder](https://drive.google.com/drive/folders/1ldncvdqIf6miiskDp_EDuGSDAaI_fJx8).
-1. Dependencies are in [pyproject.toml](./pyproject.toml). Use `poetry install` for easiest time installing. `pip install epstein-files` should also work, though `pipx install epstein-files` is usually better.
+
+#### Installation
+1. Requires you have a local copy of the OCR text files from the House Oversight document release in a directory `/path/to/epstein/ocr_txt_files`. You can download those OCR text files from [the Congressional Google Drive folder](https://drive.google.com/drive/folders/1ldncvdqIf6miiskDp_EDuGSDAaI_fJx8) (make sure you grab both the `001/` and `002/` folders).
+1. Use `poetry install` for easiest time installing. `pip install epstein-files` should also work, though `pipx install epstein-files` is usually better.
 
 You need to set the `EPSTEIN_DOCS_DIR` environment variable with the path to the folder of files you just downloaded when running. You can either create a `.env` file modeled on [`.env.example`](./.env.example) (which will set it permanently) or you can run with:
 
@@ -63,11 +65,11 @@ epstein_search Bannon
 # Or a regex:
 epstein_search '\bSteve\s*Bannon\b'
 
-# Show a file with color highlighting of keywords
+# Show a file with color highlighting of keywords:
 epstein_show 030999
 # Show both the highlighted and raw versions of the file:
 epstein_show --raw 030999
-# This also works:
+# The full filename is also accepted:
 epstein_show HOUSE_OVERSIGHT_030999
 
 # Count words used by Epstein and Bannon
@@ -77,7 +79,7 @@ epstein_word_count --name 'Jeffrey Epstein' --name 'Steve Bannon'
 epstein_diff 030999 020442
 ```
 
-The first time you run anything it will take a few minutes to fix all the data, attribute the redacted emails, etc.
+The first time you run anything it will take a few minutes to fix all the janky OCR text, attribute the redacted emails, etc. After that things will be quick.
 Run `epstein_generate --help` for command line option assistance.
 
 
@@ -98,6 +100,10 @@ for email in epstein_files.emails:
 for imessage_log in epstein_files.imessage_logs:
     do_stuff(imessage_log)
 
+# JSON files
+for json_file in epstein_files.json_files:
+    do_stuff(json_file)
+
 # Other Files
 for file in epstein_files.other_files:
     do_stuff(file)

{epstein_files-1.0.7.dist-info → epstein_files-1.0.9.dist-info}/RECORD

@@ -2,7 +2,7 @@ epstein_files/__init__.py,sha256=w68EUhAzri8a_c9HggKMfoHTvPbVAO-u3NuHVizDc7U,494
 epstein_files/count_words.py,sha256=i1pYaQzX7b9S3pyV3RM_8asbQJ1PEk8wJgLOG6Mf0D8,2966
 epstein_files/documents/communication.py,sha256=SunZdjMhR9v6y8LlQ6jhIu8vYjSndaBK0Su1mKnhfj0,2060
 epstein_files/documents/document.py,sha256=BUaioSvOmfsR-ULa6hJy3WYg-hBDC-kqafUheMJ-jFY,16665
-epstein_files/documents/email.py,sha256=jLr20lJPagAv3USE7GLY6f9neKCFWIBqeXgy1liJ6XE,38414
+epstein_files/documents/email.py,sha256=H34b2zt_TrPUgXHwZXybjmLE9-QNAtezs9NVSCPOSGM,38462
 epstein_files/documents/emails/email_header.py,sha256=wkPfSLbmzkAeQwvhf0bAeFDLPbQT-EeG0v8vNNLYktM,7502
 epstein_files/documents/imessage/text_message.py,sha256=wfWPQhwGG5Yzyhbr1NAQAY0bzRjjqVZmh8SPl48XmAM,3025
 epstein_files/documents/json_file.py,sha256=1Cx_3uM38Dwgrbs8fU55TUZKSrCsmd4QpHKWtfWdudw,1089
@@ -11,24 +11,24 @@ epstein_files/documents/other_file.py,sha256=NdVlCYcyzHvOInReqF-zvHJI1hwtzMWW9ek
 epstein_files/epstein_files.py,sha256=EEx8Auwv8z0FkRrCi7wE8iuuRQd6K1rQDMc2vdbrsh4,18298
 epstein_files/util/constant/common_words.py,sha256=aR0UjoWmxyR49XS-DtHECQ1CiA_bK8hNP6CQ1TS9yZA,3696
 epstein_files/util/constant/html.py,sha256=9U098TGzlghGg4WfxLYHyub5JGR17Dv7VP5i2MSu8Kk,1415
-epstein_files/util/constant/names.py,sha256=iwnFqIceffYyLj7AaCsh3uve4Y0WbsZvHukjA1aFJWY,10104
+epstein_files/util/constant/names.py,sha256=flIZCafFXHiaSy-G2QhYH0hNfkeJBH6Gz7p9AdvYgC0,10125
 epstein_files/util/constant/output_files.py,sha256=BkV4_gmdj46RfGy5SFYp6dgTty3FtlBth5YGmaGutls,1700
 epstein_files/util/constant/strings.py,sha256=FDtksfH50PSxtSBw9XhmqxtrgRgGxdIvGiAR2bbPpu4,1899
 epstein_files/util/constant/urls.py,sha256=0IdCVVvXib0i-4TZFkVHoS4zCbjOBZWcr6NkGxsmQWM,4981
 epstein_files/util/constants.py,sha256=MsWZQs3qd9N1HlgC7MoSKRF6ssbmWlUXX49REsp3qQs,110867
 epstein_files/util/data.py,sha256=xwTqrbAi7ZDJM0iyFVOevnokP_oIQ2npkRjHzF1KGGY,2908
 epstein_files/util/doc_cfg.py,sha256=5Pb__bP00mKi9ACv33omZQA-TBzumc7D2Td_Mk4M5DY,9822
-epstein_files/util/env.py,sha256=qAj_ueYwlfmw1oeKaW3VYSf0VP_DZcN2CFsu5hab_ig,5011
+epstein_files/util/env.py,sha256=PaPBi27-npU9egt9LHxr5qR65B2DPHwt7Xc9sx5VN-M,5225
 epstein_files/util/file_helper.py,sha256=v_bE10MHEcXti9DVJo4WqyOsG83Xrv05S3Vc70cYJkk,3082
 epstein_files/util/highlighted_group.py,sha256=L7R63oyDG_lQ9Vv5gB_rRwJgHS2sdMfXHs9xcuDzqdc,35667
-epstein_files/util/logging.py,sha256=b9iCTQkpAxu_3HphM5wm7VuPbWj9tocTuyUvMUTaI5A,2137
-epstein_files/util/output.py,sha256=siGbVIudA5hhHjekJw-OONCkrDPCqJXvy1QmkdDF1EU,7699
+epstein_files/util/logging.py,sha256=4hVl1Qw1qRMSVEYKXZxrvdQuSIMBgTPskzvNMNu8268,2185
+epstein_files/util/output.py,sha256=wLjFBGR5ffn4cLep12G3OmUR0H3WtEMXeVMOXtd-6ig,7909
 epstein_files/util/rich.py,sha256=rdHzn4XRB2erQSf2yYyPakRmd9ixqBUdS8-BVOUAXnE,14603
 epstein_files/util/search_result.py,sha256=1fxe0KPBQXBk4dLfu6m0QXIzYfZCzvaSkWqvghJGzxY,567
 epstein_files/util/timer.py,sha256=8hxW4Y1JcTUfnBrHh7sL2pM9xu1sL4HFQM4CmmzTarU,837
 epstein_files/util/word_count.py,sha256=eGzcsoAvMcutRUFOJnVuEp9_28H74to7T9jTdGUZnuI,6757
-epstein_files-1.0.7.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-epstein_files-1.0.7.dist-info/METADATA,sha256=nAeavhZZPr-pitCdDE4tCKXbexZKmZE8r-b9m_FsSiA,5612
-epstein_files-1.0.7.dist-info/WHEEL,sha256=d2fvjOD7sXsVzChCqf0Ty0JbHKBaLYwDbGQDwQTnJ50,88
-epstein_files-1.0.7.dist-info/entry_points.txt,sha256=5qYgwAXpxegeAicD_rzda_trDRnUC51F5UVDpcZ7j6Q,240
-epstein_files-1.0.7.dist-info/RECORD,,
+epstein_files-1.0.9.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+epstein_files-1.0.9.dist-info/METADATA,sha256=QTK8iM7ZkD2742Gk9c8yPyG5LV1QLNOrjKguJALSX1c,5479
+epstein_files-1.0.9.dist-info/WHEEL,sha256=d2fvjOD7sXsVzChCqf0Ty0JbHKBaLYwDbGQDwQTnJ50,88
+epstein_files-1.0.9.dist-info/entry_points.txt,sha256=5qYgwAXpxegeAicD_rzda_trDRnUC51F5UVDpcZ7j6Q,240
+epstein_files-1.0.9.dist-info/RECORD,,