epstein-files 1.0.1__py3-none-any.whl → 1.0.2__py3-none-any.whl

epstein_files/util/data.py

@@ -3,15 +3,10 @@ Helpers for dealing with various kinds of data.
 """
 import itertools
 import re
-import time
-from dataclasses import dataclass, field
 from datetime import datetime, timezone
 from dateutil import tz
 from typing import TypeVar
 
-from dateutil.parser import parse
-from rich.text import Text
-
 from epstein_files.util.constant import names
 from epstein_files.util.env import args
 from epstein_files.util.logging import logger
@@ -24,27 +19,20 @@ CONSTANT_VAR_REGEX = re.compile(r"^[A-Z_]+$")
 ALL_NAMES = [v for k, v in vars(names).items() if isinstance(v, str) and CONSTANT_VAR_REGEX.match(k)]
 
 PACIFIC_TZ = tz.gettz("America/Los_Angeles")
-TIMEZONE_INFO = {"PST": PACIFIC_TZ, "PDT": PACIFIC_TZ}  # Suppresses annoying warnings from parse() calls
-
-
-def dict_sets_to_lists(d: dict[str, set]) -> dict[str, list]:
-    return {k: sorted(list(v)) for k, v in d.items()}
-
-
-def extract_datetime(s: str) -> datetime | None:
-    match = ISO_DATE_REGEX.search(s)
+TIMEZONE_INFO = {"PDT": PACIFIC_TZ, "PST": PACIFIC_TZ}  # Suppresses annoying warnings from parse() calls
 
-    if not match:
-        return None
 
-    date_str = match.group(0)
+collapse_newlines = lambda text: MULTINEWLINE_REGEX.sub('\n\n', text)
+date_str = lambda dt: dt.isoformat()[0:10] if dt else None
+escape_double_quotes = lambda text: text.replace('"', r'\"')
+escape_single_quotes = lambda text: text.replace("'", r"\'")
+iso_timestamp = lambda dt: dt.isoformat().replace('T', ' ')
+uniquify = lambda _list: list(set(_list))
+without_nones = lambda _list: [e for e in _list if e]
 
-    if len(date_str) == 4:
-        date_str += '-01-01'
-    elif len(date_str) == 7:
-        date_str += '-01'
 
-    return parse(date_str, tzinfos=TIMEZONE_INFO)
+def dict_sets_to_lists(d: dict[str, set]) -> dict[str, list]:
+    return {k: sorted(list(v)) for k, v in d.items()}
 
 
 def extract_last_name(name: str) -> str:
@@ -91,8 +79,8 @@ def ordinal_str(n: int) -> str:
     return str(n) + suffix
 
 
-def patternize(_pattern: str | re.Pattern):
-    return _pattern if isinstance(_pattern, re.Pattern) else re.compile(rf"({_pattern})", re.IGNORECASE)
+def patternize(_pattern: str | re.Pattern) -> re.Pattern:
+    return _pattern if isinstance(_pattern, re.Pattern) else re.compile(fr"({_pattern})", re.IGNORECASE)
 
 
 def remove_timezone(timestamp: datetime) -> datetime:
@@ -106,12 +94,3 @@ def remove_timezone(timestamp: datetime) -> datetime:
 def sort_dict(d: dict[str | None, int] | dict[str, int]) -> list[tuple[str | None, int]]:
     sort_key = lambda e: (e[0] or '').lower() if args.sort_alphabetical else [-e[1], (e[0] or '').lower()]
     return sorted(d.items(), key=sort_key)
-
-
-collapse_newlines = lambda text: MULTINEWLINE_REGEX.sub('\n\n', text)
-date_str = lambda dt: dt.isoformat()[0:10] if dt else None
-escape_double_quotes = lambda text: text.replace('"', r'\"')
-escape_single_quotes = lambda text: text.replace("'", r"\'")
-iso_timestamp = lambda dt: dt.isoformat().replace('T', ' ')
-uniquify = lambda _list: list(set(_list))
-without_nones = lambda _list: [e for e in _list if e]

epstein_files/util/doc_cfg.py

@@ -116,6 +116,8 @@ class DocCfg:
                 return self.title_by_author()
             elif self.category == FINANCE and self.author in FINANCIAL_REPORTS_AUTHORS:
                 return f"{self.author} report: '{self.description}'"
+            elif self.category == LEGAL and 'v.' in self.author:
+                return f"{self.author}: '{self.description}'"
         elif self.category and self.author is None and self.description is None:
             return self.category
 
@@ -176,16 +178,6 @@ class DocCfg:
 
         return props
 
-    def __eq__(self, other: 'DocCfg') -> bool:
-        """Return True if everything matches other than the two 'dupe_' fields ('duplicate_ids' is compared)."""
-        for _field in self.sorted_fields():
-            if _field.name == 'id' or _field.name.startswith('dupe'):
-                continue
-            elif getattr(self, _field.name) != getattr(other, _field.name):
-                return False
-
-        return True
-
     def __repr__(self) -> str:
         props = self._props_strs()
         type_str = f"{type(self).__name__}("

epstein_files/util/env.py

@@ -7,15 +7,16 @@ from sys import argv
 from epstein_files.util.logging import datefinder_logger, env_log_level, logger
 
 DEFAULT_WIDTH = 154
-HTML_SCRIPTS = ['generate_html.py', 'count_words.py']
+HTML_SCRIPTS = ['epstein_generate', 'generate_html.py', 'count_words.py']
 
 
 parser = ArgumentParser(description="Parse epstein OCR docs and generate HTML page.")
-parser.add_argument('--build', '-b', action='store_true', help='write HTML to docs/index.html')
+parser.add_argument('--build', '-b', action='store_true', help='write output to file')
 parser.add_argument('--all-emails', '-ae', action='store_true', help='all the emails instead of just the interesting ones')
 parser.add_argument('--all-other-files', '-ao', action='store_true', help='all the non-email, non-text msg files instead of just interesting ones')
 parser.add_argument('--colors-only', '-c', action='store_true', help='print header with color key table and links and exit')
 parser.add_argument('--name', '-n', action='append', dest='names', help='specify the name(s) whose communications should be output')
+parser.add_argument('--output-file', '-out', metavar='FILE', default='index.html', help='write output to FILE in docs/ (default=index.html)')
 parser.add_argument('--output-emails', '-oe', action='store_true', help='generate other files section')
 parser.add_argument('--output-other-files', '-oo', action='store_true', help='generate other files section')
 parser.add_argument('--output-texts', '-ot', action='store_true', help='generate other files section')

epstein_files/util/file_helper.py

@@ -8,7 +8,6 @@ from epstein_files.util.constant.strings import FILE_NAME_REGEX, FILE_STEM_REGEX
 EPSTEIN_DOCS_DIR_ENV_VAR_NAME = 'EPSTEIN_DOCS_DIR'
 DOCS_DIR_ENV = environ[EPSTEIN_DOCS_DIR_ENV_VAR_NAME]
 DOCS_DIR = Path(DOCS_DIR_ENV or '').resolve()
-PICKLED_PATH = Path("the_epstein_files.pkl.gz")
 
 if not DOCS_DIR_ENV:
     print(f"ERROR: {EPSTEIN_DOCS_DIR_ENV_VAR_NAME} env var not set!")
@@ -17,20 +16,7 @@ elif not DOCS_DIR.exists():
     print(f"ERROR: {EPSTEIN_DOCS_DIR_ENV_VAR_NAME}='{DOCS_DIR}' does not exist!")
     exit(1)
 
-HTML_DIR = Path('docs')
 EXTRACTED_EMAILS_DIR = Path('emails_extracted_from_legal_filings')
-EPSTEIN_WORD_COUNT_HTML_PATH = HTML_DIR.joinpath('epstein_texts_and_emails_word_count.html')
-GH_PAGES_HTML_PATH = HTML_DIR.joinpath('index.html')
-JSON_METADATA_PATH = HTML_DIR.joinpath('epstein_files_nov_2025_cryptadamus_metadata.json')
-WORD_COUNT_HTML_PATH = HTML_DIR.joinpath('epstein_emails_word_count.html')
-
-BUILD_ARTIFACTS = [
-    EPSTEIN_WORD_COUNT_HTML_PATH,
-    GH_PAGES_HTML_PATH,
-    JSON_METADATA_PATH,
-    WORD_COUNT_HTML_PATH,
-]
-
 FILE_ID_REGEX = re.compile(fr".*{FILE_NAME_REGEX.pattern}")
 FILENAME_LENGTH = len(HOUSE_OVERSIGHT_PREFIX) + 6
 KB = 1024
@@ -110,11 +96,3 @@ def is_local_extract_file(filename) -> bool:
     """Return true if filename is of form 'HOUSE_OVERSIGHT_029835_1.txt'."""
     file_match = FILE_ID_REGEX.match(str(filename))
     return True if file_match and file_match.group(2) else False
-
-
-def make_clean() -> None:
-    """Delete all build artifacts."""
-    for build_file in BUILD_ARTIFACTS:
-        if build_file.exists():
-            print(f"Removing build file '{build_file}'...")
-            build_file.unlink()

epstein_files/util/highlighted_group.py

@@ -272,7 +272,7 @@ HIGHLIGHTED_NAMES = [
     HighlightedNames(
         label='europe',
         style='light_sky_blue3',
-        pattern=r'(Angela )?Merk(el|le)|Austria|(Benjamin\s*)?Harnwell|Berlin|Brexit(eers?)?|Brit(ain|ish)|Brussels|Cannes|(Caroline|Jack)?\s*Lang(, Caroline)?|Cypr(iot|us)|Davos|ECB|EU|Europe(an)?(\s*Union)?|France|Geneva|Germany?|Gillard|Gree(ce|k)|Ital(ian|y)|Jacques|(Kevin\s*)?Rudd|Le\s*Pen|London|Macron|Melusine|Munich|(Natalia\s*)?Veselnitskaya|(Nicholas\s*)?Sarkozy|Nigel(\s*Farage)?|Oslo|Paris|Polish|(Sebastian )?Kurz|(Vi(c|k)tor\s+)?Orbah?n|Edward Rod Larsen|Strasbourg|Strauss[- ]?Kahn|Swed(en|ish)(?![-\s]+America)|Switzerland|(Tony\s)?Blair|Ukrain(e|ian)|Vienna|(Vitaly\s*)?Churkin|Zug',
+        pattern=r'(Angela )?Merk(el|le)|Austria|(Benjamin\s*)?Harnwell|Berlin|Borge|Brexit(eers?)?|Brit(ain|ish)|Brussels|Cannes|(Caroline|Jack)?\s*Lang(, Caroline)?|Cypr(iot|us)|Davos|ECB|EU|Europe(an)?(\s*Union)?|France|Geneva|Germany?|Gillard|Gree(ce|k)|Ital(ian|y)|Jacques|(Kevin\s*)?Rudd|Le\s*Pen|London|Macron|Melusine|Munich|(Natalia\s*)?Veselnitskaya|(Nicholas\s*)?Sarkozy|Nigel(\s*Farage)?|Oslo|Paris|Polish|(Sebastian )?Kurz|(Vi(c|k)tor\s+)?Orbah?n|Edward Rod Larsen|Strasbourg|Strauss[- ]?Kahn|Swed(en|ish)(?![-\s]+America)|Switzerland|(Tony\s)?Blair|Ukrain(e|ian)|Vienna|(Vitaly\s*)?Churkin|Zug',
         emailers = {
             ANDRZEJ_DUDA: 'former president of Poland',
             MIROSLAV_LAJCAK: 'Russia-friendly Slovakian politician, friend of Steve Bannon',
@@ -519,7 +519,7 @@ HIGHLIGHTED_NAMES = [
     HighlightedNames(
         label='trump',
         style='red3 bold',
-        pattern=r"@?realDonaldTrump|(Alan\s*)?Weiss?elberg|\bDJ?T\b|Donald J. Tramp|(Donald\s+(J\.\s+)?)?Trump(ism|\s*Properties)?|Don(ald| *Jr)(?! Rubin)|Ivana|(Madeleine\s*)?Westerhout|Mar[-\s]*a[-\s]*Lago|(Marla\s*)?Maples|(Matt(hew)? )?Calamari|\bMatt C\b|Melania|(Michael (J.? )?)?Boccio|Roger\s+Stone|rona|(The\s*)?Art\s*of\s*the\s*Deal",
+        pattern=r"@?realDonaldTrump|(Alan\s*)?Weiss?elberg|\bDJ?T\b|Donald J. Tramp|(Donald\s+(J\.\s+)?)?Trump(ism|\s*Properties)?|Don(ald| *Jr)(?! Rubin)|Ivana|(Madeleine\s*)?Westerhout|Mar[-\s]*a[-\s]*Lago|(Marla\s*)?Maples|(Matt(hew)? )?Calamari|\bMatt C\b|Melania|(Michael (J.? )?)?Boccio|Rebekah\s*Mercer|Roger\s+Stone|rona|(The\s*)?Art\s*of\s*the\s*Deal",
         emailers = {
             'Bruce Moskowitz': "'Trump's health guy' according to Epstein",
         },

epstein_files/util/logging.py

@@ -1,5 +1,6 @@
 import logging
 from os import environ
+from pathlib import Path
 
 from rich.console import Console
 from rich.highlighter import ReprHighlighter
@@ -7,6 +8,7 @@ from rich.logging import RichHandler
 from rich.theme import Theme
 
 from epstein_files.util.constant.strings import *
+from epstein_files.util.file_helper import file_size_str
 
 FILENAME_STYLE = 'gray27'
 
@@ -55,3 +57,7 @@ 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:
+    logger.warning(f"Wrote {file_size_str(file_path)} to '{file_path}'")

epstein_files/util/output.py

@@ -0,0 +1,180 @@
+from rich.padding import Padding
+
+from epstein_files.documents.email import Email
+from epstein_files.documents.messenger_log import MessengerLog
+from epstein_files.epstein_files import EpsteinFiles, count_by_month
+from epstein_files.util.constant.output_files import JSON_METADATA_PATH
+from epstein_files.util.constant import urls
+from epstein_files.util.constant.html import *
+from epstein_files.util.constant.names import *
+from epstein_files.util.constant.strings import EMAIL_CLASS, MESSENGER_LOG_CLASS
+from epstein_files.util.data import dict_sets_to_lists
+from epstein_files.util.env import args, specified_names
+from epstein_files.util.logging import log_file_write, logger
+from epstein_files.util.rich import *
+
+PRINT_COLOR_KEY_EVERY_N_EMAILS = 150
+
+# Order matters. Default names to print emails for.
+DEFAULT_EMAILERS = [
+    JEREMY_RUBIN,
+    AL_SECKEL,
+    JOI_ITO,
+    JABOR_Y,
+    STEVEN_SINOFSKY,
+    DANIEL_SIAD,
+    JEAN_LUC_BRUNEL,
+    STEVEN_HOFFENBERG,
+    EHUD_BARAK,
+    MARTIN_NOWAK,
+    MASHA_DROKOVA,
+    RENATA_BOLOTOVA,
+    STEVE_BANNON,
+    OLIVIER_COLOM,
+    BORIS_NIKOLIC,
+    PRINCE_ANDREW,
+    JIDE_ZEITLIN,
+    DAVID_STERN,
+    MOHAMED_WAHEED_HASSAN,
+    JENNIFER_JACQUET,
+    TYLER_SHEARS,
+    CHRISTINA_GALBRAITH,
+    None,
+]
+
+# Order matters. Default names to print tables w/email subject, timestamp, etc for. # TODO: get rid of this ?
+DEFAULT_EMAILER_TABLES: list[str | None] = [
+    GHISLAINE_MAXWELL,
+    LEON_BLACK,
+    SULTAN_BIN_SULAYEM,
+    DEEPAK_CHOPRA,
+    ARIANE_DE_ROTHSCHILD,
+]
+
+if len(set(DEFAULT_EMAILERS).intersection(set(DEFAULT_EMAILER_TABLES))) > 0:
+    raise RuntimeError(f"Some names appear in both DEFAULT_EMAILERS and DEFAULT_EMAILER_TABLES")
+
+
+def print_emails(epstein_files: EpsteinFiles) -> int:
+    """Returns number of emails printed."""
+    print_section_header(('Selections from ' if not args.all_emails else '') + 'His Emails')
+    print_other_site_link(is_header=False)
+
+    emailers_to_print: list[str | None]
+    emailer_tables: list[str | None] = []
+    already_printed_emails: list[Email] = []
+    num_emails_printed_since_last_color_key = 0
+
+    if specified_names:
+        emailers_to_print = specified_names
+    else:
+        epstein_files.print_emailer_counts_table()
+
+        if args.all_emails:
+            emailers_to_print = sorted(epstein_files.all_emailers(), key=lambda e: epstein_files.earliest_email_at(e))
+            console.print('Email conversations are sorted chronologically based on time of the first email.')
+            print_numbered_list_of_emailers(emailers_to_print, epstein_files)
+        else:
+            emailers_to_print = DEFAULT_EMAILERS
+            emailer_tables = DEFAULT_EMAILER_TABLES
+            console.print('Email conversations grouped by counterparty can be found in the order listed below.')
+            print_numbered_list_of_emailers(emailers_to_print)
+            console.print("\nAfter that there's tables linking to (but not displaying) all known emails for each of these people:")
+            print_numbered_list_of_emailers(emailer_tables)
+
+    for author in emailers_to_print:
+        author_emails = epstein_files.print_emails_for(author)
+        already_printed_emails.extend(author_emails)
+        num_emails_printed_since_last_color_key += len(author_emails)
+
+        # Print color key every once in a while
+        if num_emails_printed_since_last_color_key > PRINT_COLOR_KEY_EVERY_N_EMAILS:
+            print_color_key()
+            num_emails_printed_since_last_color_key = 0
+
+    if emailer_tables:
+        print_author_header(f"Email Tables for {len(emailer_tables)} Other People", 'white')
+
+        for name in DEFAULT_EMAILER_TABLES:
+            epstein_files.print_emails_table_for(name)
+
+    if not specified_names:
+        epstein_files.print_email_device_info()
+
+    if args.all_emails:
+        _verify_all_emails_printed(epstein_files, already_printed_emails)
+
+    logger.warning(f"Rewrote {len(Email.rewritten_header_ids)} headers of {len(epstein_files.emails)} emails")
+    return len(already_printed_emails)
+
+
+def print_json_metadata(epstein_files: EpsteinFiles) -> None:
+    json_str = epstein_files.json_metadata()
+
+    if args.build:
+        with open(JSON_METADATA_PATH, 'w') as f:
+            f.write(json_str)
+            log_file_write(JSON_METADATA_PATH)
+    else:
+        console.print_json(json_str, indent=4, sort_keys=True)
+
+
+def print_json_stats(epstein_files: EpsteinFiles) -> None:
+    console.line(5)
+    console.print(Panel('JSON Stats Dump', expand=True, style='reverse bold'), '\n')
+    print_json(f"{MESSENGER_LOG_CLASS} Sender Counts", MessengerLog.count_authors(epstein_files.imessage_logs), skip_falsey=True)
+    print_json(f"{EMAIL_CLASS} Author Counts", epstein_files.email_author_counts, skip_falsey=True)
+    print_json(f"{EMAIL_CLASS} Recipient Counts", epstein_files.email_recipient_counts, skip_falsey=True)
+    print_json("Email signature_substitution_countss", epstein_files.email_signature_substitution_counts(), skip_falsey=True)
+    print_json("email_author_device_signatures", dict_sets_to_lists(epstein_files.email_authors_to_device_signatures))
+    print_json("email_sent_from_devices", dict_sets_to_lists(epstein_files.email_device_signatures_to_authors))
+    print_json("email_unknown_recipient_file_ids", epstein_files.email_unknown_recipient_file_ids())
+    print_json("count_by_month", count_by_month(epstein_files.all_documents()))
+
+
+def print_text_messages(epstein_files: EpsteinFiles) -> None:
+    print_section_header('Text Messages')
+    print_centered("(conversations are sorted chronologically based on timestamp of first message)\n", style='gray30')
+    authors: list[str | None] = specified_names if specified_names else [JEFFREY_EPSTEIN]
+    log_files = epstein_files.imessage_logs_for(authors)
+
+    for log_file in log_files:
+        console.print(Padding(log_file))
+        console.line(2)
+
+    epstein_files.print_imessage_summary()
+
+
+def write_urls() -> None:
+    if args.output_file == 'index.html':
+        logger.warning(f"Can't write env vars to '{args.output_file}', writing to '{URLS_ENV}' instead.\n")
+        args.output_file = URLS_ENV
+
+    url_vars = {
+        k: v for k, v in vars(urls).items()
+        if isinstance(v, str) and \
+            k.split('_')[-1] in ['URL'] and \
+            'michelcrypt4d4mus' in v and \
+            'github.com' not in v and \
+            'BASE' not in v
+    }
+
+    with open(args.output_file, 'w') as f:
+        for var_name, url in url_vars.items():
+            key_value = f"{var_name}='{url}'"
+            console.print(key_value, style='dim')
+            f.write(f"{key_value}\n")
+
+    console.line()
+    logger.warning(f"Wrote {len(url_vars)} URL variables to '{args.output_file}'\n")
+
+
+
+def _verify_all_emails_printed(epstein_files: EpsteinFiles, already_printed_emails: list[Email]) -> None:
+    """Log warnings if some emails were never printed."""
+    email_ids_that_were_printed = set([email.file_id for email in already_printed_emails])
+    logger.warning(f"Printed {len(already_printed_emails)} emails of {len(email_ids_that_were_printed)} unique file IDs.")
+
+    for email in epstein_files.emails:
+        if email.file_id not in email_ids_that_were_printed and not email.is_duplicate:
+            logger.warning(f"Failed to print {email.summary()}")

epstein_files/util/rich.py

@@ -2,7 +2,6 @@
 import json
 from os import devnull
 from pathlib import Path
-from typing import Literal
 
 from rich.align import Align
 from rich.console import Console, RenderableType
@@ -20,9 +19,8 @@ from epstein_files.util.constant.urls import *
 from epstein_files.util.constants import FALLBACK_TIMESTAMP, HEADER_ABBREVIATIONS
 from epstein_files.util.data import json_safe
 from epstein_files.util.env import args
-from epstein_files.util.file_helper import file_size_str
 from epstein_files.util.highlighted_group import ALL_HIGHLIGHTS, HIGHLIGHTED_NAMES, EpsteinHighlighter
-from epstein_files.util.logging import logger
+from epstein_files.util.logging import log_file_write, logger
 
 TITLE_WIDTH = 50
 NUM_COLOR_KEY_COLS = 4
@@ -73,6 +71,14 @@ def add_cols_to_table(table: Table, col_names: list[str]) -> None:
         table.add_column(col, justify='left' if i == 0 else 'center')
 
 
+def build_highlighter(pattern: str) -> EpsteinHighlighter:
+    class TempHighlighter(EpsteinHighlighter):
+        """rich.highlighter that finds and colors interesting keywords based on the above config."""
+        highlights = EpsteinHighlighter.highlights + [re.compile(fr"(?P<trump>{pattern})", re.IGNORECASE)]
+
+    return TempHighlighter()
+
+
 def join_texts(txts: list[Text], join: str = ' ', encloser: str = '') -> Text:
     """Join rich.Text objs into one."""
     if encloser:
@@ -91,8 +97,11 @@ def join_texts(txts: list[Text], join: str = ' ', encloser: str = '') -> Text:
     return txt
 
 
-def key_value_txt(key: str, value: Text | str) -> Text:
+def key_value_txt(key: str, value: Text | int | str) -> Text:
     """Generate a Text obj for 'key=value'."""
+    if isinstance(value, int):
+        value = Text(f"{value}", style='cyan')
+
     return Text('').append(key, style=KEY_STYLE).append('=', style=SYMBOL_STYLE).append(value)
 
 
@@ -219,10 +228,8 @@ def print_other_site_link(is_header: bool = True) -> None:
     print_centered(parenthesize(Text.from_markup(markup_msg)), style='bold')
     word_count_link = link_text_obj(WORD_COUNT_URL, 'site showing the most frequently used words in these communiques', OTHER_SITE_LINK_STYLE)
     print_centered(parenthesize(word_count_link))
-
-    if is_header:
-        metadata_link = link_text_obj(JSON_METADATA_URL, 'file metadata containing author attribution explanations', OTHER_SITE_LINK_STYLE)
-        print_centered(parenthesize(metadata_link))
+    metadata_link = link_text_obj(JSON_METADATA_URL, 'metadata with author attribution explanations', OTHER_SITE_LINK_STYLE)
+    print_centered(parenthesize(metadata_link))
 
 
 def print_page_title(expand: bool = True, width: int | None = None) -> None:
@@ -298,7 +305,7 @@ def write_html(output_path: Path) -> None:
         return
 
     console.save_html(str(output_path), code_format=CONSOLE_HTML_FORMAT, theme=HTML_TERMINAL_THEME)
-    logger.warning(f"Wrote {file_size_str(output_path)} to '{output_path}'")
+    log_file_write(output_path)
 
 
 def _print_abbreviations_table() -> None:

{epstein_files-1.0.1.dist-info → epstein_files-1.0.2.dist-info}/METADATA

@@ -1,26 +1,41 @@
 Metadata-Version: 2.1
 Name: epstein-files
-Version: 1.0.1
+Version: 1.0.2
 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
+Keywords: Epstein,Jeffrey Epstein
 Author: Michel de Cryptadamus
 Requires-Python: >=3.11,<4.0
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Information Technology
+Classifier: License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)
+Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: datefinder (>=0.7.3,<0.8.0)
 Requires-Dist: inflection (>=0.5.1,<0.6.0)
 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)
+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: TextMessages, https://michelcrypt4d4mus.github.io/epstein_text_messages
+Project-URL: WordCounts, https://michelcrypt4d4mus.github.io/epstein_text_messages/communication_word_count_epstein_files_nov_2025.html
 Description-Content-Type: text/markdown
 
 # I Made Epstein's Text Messages Great Again
 
 * [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 counts of sent emails to/from Epstein) generated by this code can be viewed [here](https://michelcrypt4d4mus.github.io/epstein_text_messages/).
-* All of His Emails can be read at another page also generated by this code [here](https://michelcrypt4d4mus.github.io/epstein_emails_house_oversight/).
-* Word counts for the emails and text messages are [here](https://michelcrypt4d4mus.github.io/epstein_text_messages/epstein_emails_word_count.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/epstein_files_nov_2025_cryptadamus_metadata.json)
+* All of His Emails can be read at another page also generated by this code [here](https://michelcrypt4d4mus.github.io/epstein_text_messages/all_emails_epstein_files_nov_2025.html).
+* Word counts for the emails and text messages are [here](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` should also appear in the JSON metadata.
 
 

epstein_files-1.0.2.dist-info/RECORD

@@ -0,0 +1,33 @@
+epstein_files/__init__.py,sha256=N4-A81KlSNWXyliBsjooi6GZr9_2qIB08qTG5RE9GzA,4725
+epstein_files/documents/communication.py,sha256=SunZdjMhR9v6y8LlQ6jhIu8vYjSndaBK0Su1mKnhfj0,2060
+epstein_files/documents/document.py,sha256=MOTS6AZFNOqnzpvYLXvoJC05ZVL9lTZnsRc-qjAjcJ4,16515
+epstein_files/documents/email.py,sha256=IpKeOuLTmHWowBvUUEp-tyTC8pwEmXg3XgLJkplQZWg,37717
+epstein_files/documents/emails/email_header.py,sha256=wkPfSLbmzkAeQwvhf0bAeFDLPbQT-EeG0v8vNNLYktM,7502
+epstein_files/documents/imessage/text_message.py,sha256=DMdd__L7UPad0YS49MJf_3bTVyE1BLfWafQbDQierC8,3272
+epstein_files/documents/json_file.py,sha256=Vf9iHiEhUqk-hEh6lGZX_mJNWZUUQWeT-UI3FhKW0hw,1101
+epstein_files/documents/messenger_log.py,sha256=-hSMFH_dyrjGLdph4SU2xQK4RpXOhkR3R_nqRrz3e1w,5620
+epstein_files/documents/other_file.py,sha256=JbKDtNrQ1Ua5vGPlZayON5Kgy0oJ-gHcdO9l9Iv9wRo,8930
+epstein_files/epstein_files.py,sha256=NpgQaxM3cC8CsAbzCyysakMbPdASWAt-wOhPZ879ZyQ,18018
+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=g0s9NA4zIexDGG7u5x0KDpLB9fyrYaYatsBhf_lH688,10253
+epstein_files/util/constant/output_files.py,sha256=B2qEXfNI_gT2Vp5HGSld2xM0PfeZ27j65HNymSmyzX4,974
+epstein_files/util/constant/strings.py,sha256=3JTqD0luJrC3NbGXn4q6P-gIaaNVx36P1oCmp92gAoM,1750
+epstein_files/util/constant/urls.py,sha256=x7Lv8yNNNLGU3GCvG4YbJ4qX3s_hiXffYuYUCjXyfbg,5526
+epstein_files/util/constants.py,sha256=xME94iH9a4b95N4yABs20Gn3Tu3cwmx5kNE_fPhsJEM,103420
+epstein_files/util/data.py,sha256=P4D_ggNNyScpTnu9wow8-67BlZtAXFKulJ5zbGtBR9A,2907
+epstein_files/util/doc_cfg.py,sha256=6H5EFLxG0ABG4BJHIEL7PSMBVwkcyjH1vvmitSQRa48,9615
+epstein_files/util/env.py,sha256=A2hEVg1HYymGd2odrLLo6k7yIvu0hh1XZniUW2u21dM,4734
+epstein_files/util/file_helper.py,sha256=v_bE10MHEcXti9DVJo4WqyOsG83Xrv05S3Vc70cYJkk,3082
+epstein_files/util/highlighted_group.py,sha256=7MfES52q10eq35L93iTIr_v5v0bamdQKCf7hlDIy7O8,35196
+epstein_files/util/logging.py,sha256=GjmOYiWAF1R_0Dvb5kXHAgPH5UJs-_gGcRig7LEDDL0,2066
+epstein_files/util/output.py,sha256=YH_-1YyNxiO29N88jvSAePbK5n25tgEIDFyP3sNNnnI,7309
+epstein_files/util/rich.py,sha256=gvSbWc-PQC5cAUg8zn02yZQkU57ExG1ArRLMIPrVxOc,13597
+epstein_files/util/search_result.py,sha256=1fxe0KPBQXBk4dLfu6m0QXIzYfZCzvaSkWqvghJGzxY,567
+epstein_files/util/timer.py,sha256=8hxW4Y1JcTUfnBrHh7sL2pM9xu1sL4HFQM4CmmzTarU,837
+epstein_files/util/word_count.py,sha256=XTINgLm01jFQlNgdiLCcVFCodXAIb1dNbaAvznoRb1o,6757
+epstein_files-1.0.2.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+epstein_files-1.0.2.dist-info/METADATA,sha256=Wf4rPDzdGRxogbs0H8cZoFb7HsRTrkPvkYHdClbg74c,4653
+epstein_files-1.0.2.dist-info/WHEEL,sha256=d2fvjOD7sXsVzChCqf0Ty0JbHKBaLYwDbGQDwQTnJ50,88
+epstein_files-1.0.2.dist-info/entry_points.txt,sha256=EV9qTh_n9X_1MOiQnxG5hM6R5v0rfi8W4QE-bsZkw3o,238
+epstein_files-1.0.2.dist-info/RECORD,,

epstein_files-1.0.2.dist-info/entry_points.txt

@@ -0,0 +1,7 @@
+[console_scripts]
+epstein_diff=epstein_files:epstein_diff
+epstein_dump_urls=epstein_files:epstein_dump_urls
+epstein_generate=epstein_files:generate_html
+epstein_search=epstein_files:epstein_search
+epstein_show=epstein_files:epstein_show
+

epstein_files-1.0.1.dist-info/RECORD

@@ -1,30 +0,0 @@
-epstein_files/__init__.py,sha256=HKOGWVzyiEl0II8s7qnO33wcTZPw8dr3HDfT7_VnY2U,7831
-epstein_files/documents/communication.py,sha256=SunZdjMhR9v6y8LlQ6jhIu8vYjSndaBK0Su1mKnhfj0,2060
-epstein_files/documents/document.py,sha256=E2VUuHSoam8r8pyRbWy68_cVFU9DJ0irbtYULaDBYzE,16378
-epstein_files/documents/email.py,sha256=IpKeOuLTmHWowBvUUEp-tyTC8pwEmXg3XgLJkplQZWg,37717
-epstein_files/documents/emails/email_header.py,sha256=wkPfSLbmzkAeQwvhf0bAeFDLPbQT-EeG0v8vNNLYktM,7502
-epstein_files/documents/imessage/text_message.py,sha256=DMdd__L7UPad0YS49MJf_3bTVyE1BLfWafQbDQierC8,3272
-epstein_files/documents/json_file.py,sha256=Vf9iHiEhUqk-hEh6lGZX_mJNWZUUQWeT-UI3FhKW0hw,1101
-epstein_files/documents/messenger_log.py,sha256=-hSMFH_dyrjGLdph4SU2xQK4RpXOhkR3R_nqRrz3e1w,5620
-epstein_files/documents/other_file.py,sha256=JbKDtNrQ1Ua5vGPlZayON5Kgy0oJ-gHcdO9l9Iv9wRo,8930
-epstein_files/epstein_files.py,sha256=ruhl24FgOpEdcqbMcIpgyYlqEBi1ZeztQ7QmZMYANp0,17856
-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=eSgHnOqMAy7Czfw1vJ3lvniDST7QpfuQ8XgzttXpAi8,10191
-epstein_files/util/constant/strings.py,sha256=3JTqD0luJrC3NbGXn4q6P-gIaaNVx36P1oCmp92gAoM,1750
-epstein_files/util/constant/urls.py,sha256=P_nnb5cIrJ2NCbd4CoRfilZ5jrOzFs30jNK50F7IjZw,5483
-epstein_files/util/constants.py,sha256=l0TrpncCJcecar5geggLVfOJVhicWcu3zws-62Cslzg,102472
-epstein_files/util/data.py,sha256=s7EgmQ6SC6MoUMhP8GaxglJOJpU_nRmwI-T2inLl8hs,3329
-epstein_files/util/doc_cfg.py,sha256=AFLBp9PO2tBUYhTeNztpkWs69VPr41fCuA22IesM59g,9914
-epstein_files/util/env.py,sha256=9wM4mKPZoJO9J5VKLP67ZR1IEMkH2UaGdIaYm2tptMQ,4581
-epstein_files/util/file_helper.py,sha256=ea428og2gyUsMWd2GFldmAGvuqGNNHaTc7gGGSM_0aI,3827
-epstein_files/util/highlighted_group.py,sha256=UO0pqQH29JHiOMK2psIozIeA0zinDkql-NYDGRmFUzA,35173
-epstein_files/util/logging.py,sha256=0mABrI5TvodLDe-9svHv3YaIdSyr8PXFcu4nntW1WsI,1858
-epstein_files/util/rich.py,sha256=cLkiSg3f68bUxobzRiBRfrgS7Ya-FK7ltpQcZXNHMX4,13317
-epstein_files/util/search_result.py,sha256=1fxe0KPBQXBk4dLfu6m0QXIzYfZCzvaSkWqvghJGzxY,567
-epstein_files/util/timer.py,sha256=8hxW4Y1JcTUfnBrHh7sL2pM9xu1sL4HFQM4CmmzTarU,837
-epstein_files/util/word_count.py,sha256=XTINgLm01jFQlNgdiLCcVFCodXAIb1dNbaAvznoRb1o,6757
-epstein_files-1.0.1.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-epstein_files-1.0.1.dist-info/METADATA,sha256=IK5B-ltx_L0-EK2Oq2Q2gVXWlhYqKoYw6HCFisqitvQ,3587
-epstein_files-1.0.1.dist-info/WHEEL,sha256=d2fvjOD7sXsVzChCqf0Ty0JbHKBaLYwDbGQDwQTnJ50,88
-epstein_files-1.0.1.dist-info/RECORD,,