epstein-files 1.1.0__py3-none-any.whl → 1.1.3__py3-none-any.whl

epstein_files/util/logging.py

@@ -1,5 +1,6 @@
 import logging
 from os import environ
+from sys import exit
 
 import datefinder
 import rich_argparse_plus
@@ -39,7 +40,7 @@ class LogHighlighter(ReprHighlighter):
 
 log_console = Console(color_system='256', theme=Theme(LOG_THEME))
 log_handler = RichHandler(console=log_console, highlighter=LogHighlighter())
-logging.basicConfig(level="NOTSET", format="%(message)s", datefmt="[%X]", handlers=[log_handler])
+logging.basicConfig(level="NOTSET", format="%(message)s", datefmt=" ", handlers=[log_handler])
 logger = logging.getLogger("rich")
 
 
@@ -58,3 +59,9 @@ 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)
+
+
+def exit_with_error(msg: str) -> None:
+    print('')
+    logger.error(msg + '\n')
+    exit(1)

epstein_files/util/output.py

@@ -3,7 +3,7 @@ import json
 from rich.padding import Padding
 
 from epstein_files.documents.document import Document
-from epstein_files.documents.email import Email
+from epstein_files.documents.email import KRASSNER_RECIPIENTS, Email
 from epstein_files.documents.messenger_log import MessengerLog
 from epstein_files.documents.other_file import FIRST_FEW_LINES, OtherFile
 from epstein_files.epstein_files import EpsteinFiles, count_by_month
@@ -11,10 +11,11 @@ from epstein_files.util.constant import output_files
 from epstein_files.util.constant.html import *
 from epstein_files.util.constant.names import *
 from epstein_files.util.constant.output_files import JSON_FILES_JSON_PATH, JSON_METADATA_PATH
-from epstein_files.util.constant.strings import TIMESTAMP_DIM
-from epstein_files.util.data import dict_sets_to_lists
+from epstein_files.util.constant.strings import TIMESTAMP_DIM, TIMESTAMP_STYLE
+from epstein_files.util.data import dict_sets_to_lists, sort_dict
 from epstein_files.util.env import args
 from epstein_files.util.file_helper import log_file_write
+from epstein_files.util.highlighted_group import QUESTION_MARKS_TXT
 from epstein_files.util.logging import logger
 from epstein_files.util.rich import *
 
@@ -35,53 +36,71 @@ DEFAULT_EMAILERS = [
     EHUD_BARAK,
     MARTIN_NOWAK,
     STEVE_BANNON,
+    TYLER_SHEARS,
     JIDE_ZEITLIN,
+    CHRISTINA_GALBRAITH,
     DAVID_STERN,
     MOHAMED_WAHEED_HASSAN,
     JENNIFER_JACQUET,
-    TYLER_SHEARS,
-    CHRISTINA_GALBRAITH,
     ZUBAIR_KHAN,
     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,
-    PRINCE_ANDREW,
-    SULTAN_BIN_SULAYEM,
-    ARIANE_DE_ROTHSCHILD,
+INVALID_FOR_EPSTEIN_WEB = JUNK_EMAILERS + KRASSNER_RECIPIENTS + [
+    'ACT for America',
+    'BS Stern',
+    INTELLIGENCE_SQUARED,
+    UNKNOWN,
 ]
 
-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_email_timeline(epstein_files: EpsteinFiles) -> None:
+    """Print a table of all emails in chronological order."""
+    emails = [email for email in epstein_files.non_duplicate_emails() if not email.is_junk_mail()]
+    table = build_table(f'All {len(emails):,} Non-Junk Emails in Chronological Order', highlight=True)
+    table.add_column('ID', style=TIMESTAMP_DIM)
+    table.add_column('Sent At', style='dim')
+    table.add_column('Author', max_width=20)
+    table.add_column('Recipients', max_width=22)
+    table.add_column('Length', justify='right', style='wheat4')
+    table.add_column('Subject')
+
+    for email in Document.sort_by_timestamp(emails):
+        if email.is_junk_mail():
+            continue
+
+        table.add_row(
+            email.epstein_media_link(link_txt=email.source_file_id()),
+            email.timestamp_without_seconds(),
+            email.author_txt(),
+            email.recipients_txt(max_full_names=1),
+            f"{email.length()}",
+            email.subject(),
+        )
+
+    console.line(2)
+    console.print(table)
 
 
 def print_emails_section(epstein_files: EpsteinFiles) -> list[Email]:
     """Returns emails that were printed (may contain dupes if printed for both author and recipient)."""
     print_section_header(('Selections from ' if not args.all_emails else '') + 'His Emails')
-    print_other_page_link(epstein_files)
     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 args.names:
         emailers_to_print = args.names
     else:
-        print_centered(Padding(epstein_files.table_of_emailers(), (2, 0)))
-
         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)
+
+        print_other_page_link(epstein_files)
+        console.line(2)
+        console.print(_table_of_selected_emailers(emailers_to_print, epstein_files))
+        console.print(Padding(_all_emailers_table(epstein_files), (2, 0)))
 
     for author in emailers_to_print:
         author_emails = epstein_files.print_emails_for(author)
@@ -93,12 +112,6 @@ def print_emails_section(epstein_files: EpsteinFiles) -> list[Email]:
             print_color_key()
             num_emails_printed_since_last_color_key = 0
 
-    if emailer_tables:
-        print_author_panel(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 args.names:
         epstein_files.print_email_device_info()
 
@@ -112,8 +125,9 @@ def print_emails_section(epstein_files: EpsteinFiles) -> list[Email]:
 
 
 def print_json_files(epstein_files: EpsteinFiles):
+    """Print all the JsonFile objects"""
     if args.build:
-        json_data = {json_file.url_slug: json_file.json_data() for json_file in epstein_files.json_files}
+        json_data = {jf.url_slug: jf.json_data() for jf in epstein_files.json_files}
 
         with open(JSON_FILES_JSON_PATH, 'w') as f:
             f.write(json.dumps(json_data, sort_keys=True))
@@ -125,6 +139,17 @@ def print_json_files(epstein_files: EpsteinFiles):
             console.print_json(json_file.json_str(), indent=4, sort_keys=False)
 
 
+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')
@@ -140,72 +165,32 @@ def print_json_stats(epstein_files: EpsteinFiles) -> None:
 
 def print_other_files_section(files: list[OtherFile], epstein_files: EpsteinFiles) -> None:
     """Returns the OtherFile objects that were interesting enough to print."""
-    category_table = OtherFile.count_by_category_table(files)
-    other_files_preview_table = OtherFile.files_preview_table(files)
-    header_pfx = '' if args.all_other_files else 'Selected '
-    print_section_header(f"{FIRST_FEW_LINES} of {len(files)} {header_pfx}Files That Are Neither Emails Nor Text Messages")
-
-    if args.all_other_files:
-        console.line(1)
-    else:
-        print_other_page_link(epstein_files)
-        console.line(2)
-
-        for table in [category_table, other_files_preview_table]:
-            table.title = f"{header_pfx}{table.title}"
-
-    print_centered(category_table)
-    console.line(2)
+    title_pfx = '' if args.all_other_files else 'Selected '
+    category_table = OtherFile.count_by_category_table(files, title_pfx=title_pfx)
+    other_files_preview_table = OtherFile.files_preview_table(files, title_pfx=title_pfx)
+    print_section_header(f"{FIRST_FEW_LINES} of {len(files)} {title_pfx}Files That Are Neither Emails Nor Text Messages")
+    print_other_page_link(epstein_files)
+    print_centered(Padding(category_table, (2, 0)))
     console.print(other_files_preview_table)
 
 
-def print_text_messages_section(epstein_files: EpsteinFiles) -> None:
+def print_text_messages_section(imessage_logs: list[MessengerLog]) -> None:
     """Print summary table and stats for text messages."""
-    print_section_header('All of His Text Messages')
-    print_centered("(conversations are sorted chronologically based on timestamp of first message)\n", style='gray30')
-
-    for log_file in epstein_files.imessage_logs:
-        console.print(Padding(log_file))
-        console.line(2)
-
-    print_centered(MessengerLog.summary_table(epstein_files.imessage_logs))
-
-
-def write_complete_emails_timeline(epstein_files: EpsteinFiles) -> None:
-    table = build_table('All Non-Junk Emails In Chronological Order', highlight=True)
-    table.add_column('ID', style='dim')
-    table.add_column('Sent At', style=TIMESTAMP_DIM)
-    table.add_column('Author', max_width=22)
-    table.add_column('Recipients', max_width=30)
-    table.add_column('Length', justify='right', style='wheat4')
-    table.add_column('Subject')
-
-    for email in Document.sort_by_timestamp(epstein_files.non_duplicate_emails()):
-        if email.is_junk_mail():
-            continue
-
-        table.add_row(
-            email.source_file_id(),
-            email.epstein_media_link(link_txt=email.timestamp_without_seconds()),
-            email.author_txt,
-            email.recipients_txt(max_full_names=1),
-            f"{email.length()}",
-            email.subject(),
-        )
+    if not imessage_logs:
+        logger.warning(f"No MessengerLog objects to output...")
+        return
 
+    print_section_header('All of His Text Messages')
+    print_centered("(conversations are sorted chronologically based on timestamp of first message in the log file)", style='dim')
     console.line(2)
-    console.print(table)
-
 
-def write_json_metadata(epstein_files: EpsteinFiles) -> None:
-    json_str = epstein_files.json_metadata()
+    if not args.names:
+        print_centered(MessengerLog.summary_table(imessage_logs))
+        console.line(2)
 
-    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)
+    for log_file in imessage_logs:
+        console.print(Padding(log_file))
+        console.line(2)
 
 
 def write_urls() -> None:
@@ -230,6 +215,115 @@ def write_urls() -> None:
     logger.warning(f"Wrote {len(url_vars)} URL variables to '{URLS_ENV}'\n")
 
 
+def _all_emailers_table(epstein_files: EpsteinFiles) -> Table:
+    attributed_emails = [e for e in epstein_files.non_duplicate_emails() if e.author]
+    footer = f"(identified {len(epstein_files.email_author_counts)} authors of {len(attributed_emails):,}"
+    footer = f"{footer} out of {len(epstein_files.non_duplicate_emails()):,} emails)"
+    counts_table = build_table("All of the Email Counterparties Who Appear in the Files", caption=footer)
+
+    add_cols_to_table(counts_table, [
+        'Name',
+        {'name': 'Count', 'justify': 'right', 'style': 'bold bright_white'},
+        {'name': 'Sent', 'justify': 'right', 'style': 'gray74'},
+        {'name': 'Recv', 'justify': 'right', 'style': 'gray74'},
+        {'name': 'First', 'style': TIMESTAMP_STYLE},
+        {'name': 'Last', 'style': LAST_TIMESTAMP_STYLE},
+        {'name': 'Days', 'justify': 'right', 'style': 'dim'},
+        JMAIL,
+        EPSTEIN_MEDIA,
+        EPSTEIN_WEB,
+        'Twitter',
+    ])
+
+    emailer_counts = {
+        emailer: epstein_files.email_author_counts[emailer] + epstein_files.email_recipient_counts[emailer]
+        for emailer in epstein_files.all_emailers(True)
+    }
+
+    for name, count in sort_dict(emailer_counts):
+        style = get_style_for_name(name, default_style=DEFAULT_NAME_STYLE)
+        emails = epstein_files.emails_for(name)
+
+        counts_table.add_row(
+            Text.from_markup(link_markup(epsteinify_name_url(name or UNKNOWN), name or UNKNOWN, style)),
+            f"{count:,}",
+            str(epstein_files.email_author_counts[name]),
+            str(epstein_files.email_recipient_counts[name]),
+            emails[0].date_str(),
+            emails[-1].date_str(),
+            f"{epstein_files.email_conversation_length_in_days(name)}",
+            link_text_obj(search_jmail_url(name), JMAIL) if name else '',
+            link_text_obj(epstein_media_person_url(name), EPSTEIN_MEDIA) if _is_ok_for_epstein_web(name) else '',
+            link_text_obj(epstein_web_person_url(name), EPSTEIN_WEB) if _is_ok_for_epstein_web(name) else '',
+            link_text_obj(search_twitter_url(name), 'search X') if name else '',
+        )
+
+    return counts_table
+
+
+def _is_ok_for_epstein_web(name: str | None) -> bool:
+    """Return True if it's likely that EpsteinWeb has a page for this name."""
+    if name is None or ' ' not in name:
+        return False
+    elif '@' in name or '/' in name or '??' in name:
+        return False
+    elif name in INVALID_FOR_EPSTEIN_WEB:
+        return False
+
+    return True
+
+
+def _table_of_selected_emailers(_list: list[str | None], epstein_files: EpsteinFiles) -> Table:
+    """Add the first emailed_at timestamp for each emailer if 'epstein_files' provided."""
+    header_pfx = '' if args.all_emails else 'Selected '
+    table = build_table(f'{header_pfx}Email Conversations Grouped by Counterparty Will Appear in this Order')
+    table.add_column('Start Date')
+    table.add_column('Name', max_width=25, no_wrap=True)
+    table.add_column('Category', justify='center', style='dim italic')
+    table.add_column('Num', justify='right', style='wheat4')
+    table.add_column('Info', style='white italic')
+    current_year = 1990
+    current_year_month = current_year * 12
+    grey_idx = 0
+
+    for i, name in enumerate(_list):
+        earliest_email_date = (epstein_files.earliest_email_at(name) or FALLBACK_TIMESTAMP).date()
+        year_months = (earliest_email_date.year * 12) + earliest_email_date.month
+
+        # Color year rollovers more brightly
+        if current_year != earliest_email_date.year:
+            grey_idx = 0
+        elif current_year_month != year_months:
+            grey_idx = ((current_year_month - 1) % 12) + 1
+
+        current_year_month = year_months
+        current_year = earliest_email_date.year
+        category = get_category_txt_for_name(name)
+        info = get_info_for_name(name)
+        style = get_style_for_name(name, default_style='none')
+
+        if category and category.plain == 'paula':  # TODO: hacky
+            category = None
+        elif category and info:
+            info = info.removeprefix(f"{category.plain}, ").removeprefix(category.plain)
+        elif not name:
+            info = Text('(emails whose author or recipient could not be determined)', style='medium_purple4')
+        elif name in JUNK_EMAILERS:
+            category = Text('junk', style='gray30')
+        elif style == 'none' and '@' not in name and not (category or info):
+            info = QUESTION_MARKS_TXT
+
+        table.add_row(
+            Text(str(earliest_email_date), style=f"grey{GREY_NUMBERS[grey_idx]}"),
+            Text(name or UNKNOWN, style=get_style_for_name(name or UNKNOWN, default_style='dim')),
+            category,
+            f"{len(epstein_files.emails_for(name)):,}",
+            info or '',
+        )
+
+    return table
+
+
 def _verify_all_emails_were_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])

epstein_files/util/rich.py

@@ -20,25 +20,27 @@ from epstein_files.util.constants import FALLBACK_TIMESTAMP, HEADER_ABBREVIATION
 from epstein_files.util.data import json_safe
 from epstein_files.util.env import args
 from epstein_files.util.file_helper import log_file_write
-from epstein_files.util.highlighted_group import ALL_HIGHLIGHTS, HIGHLIGHTED_NAMES, EpsteinHighlighter
+from epstein_files.util.highlighted_group import (ALL_HIGHLIGHTS, HIGHLIGHTED_NAMES, EpsteinHighlighter,
+     get_category_txt_for_name, get_info_for_name, get_style_for_name)
 from epstein_files.util.logging import logger
 
 TITLE_WIDTH = 50
+MIN_AUTHOR_PANEL_WIDTH = 80
 NUM_COLOR_KEY_COLS = 4
 NA_TXT = Text(NA, style='dim')
-QUESTION_MARK_TXT = Text(QUESTION_MARKS, style='dim')
 GREY_NUMBERS = [58, 39, 39, 35, 30, 27, 23, 23, 19, 19, 15, 15, 15]
 
 DEFAULT_NAME_STYLE = 'gray46'
 INFO_STYLE = 'white dim italic'
-KEY_STYLE='honeydew2 bold'
-LAST_TIMESTAMP_STYLE='wheat4'
+KEY_STYLE = 'honeydew2 bold'
+LAST_TIMESTAMP_STYLE = 'wheat4'
+OTHER_PAGE_MSG_STYLE = 'gray78 dim'
 SECTION_HEADER_STYLE = 'bold white on blue3'
 SOCIAL_MEDIA_LINK_STYLE = 'pale_turquoise4'
 SUBSTACK_POST_LINK_STYLE = 'bright_cyan'
 SYMBOL_STYLE = 'grey70'
 TABLE_BORDER_STYLE = 'grey46'
-TABLE_TITLE_STYLE = f"gray85 italic"
+TABLE_TITLE_STYLE = f"gray54 italic"
 TITLE_STYLE = 'black on bright_white bold'
 
 AUX_SITE_LINK_STYLE = 'dark_orange3'
@@ -46,6 +48,7 @@ OTHER_SITE_LINK_STYLE = 'dark_goldenrod'
 
 DEFAULT_TABLE_KWARGS = {
     'border_style': TABLE_BORDER_STYLE,
+    'caption_style': 'navajo_white3 dim italic',
     'header_style': "bold",
     'title_style': TABLE_TITLE_STYLE,
 }
@@ -82,15 +85,21 @@ highlighter = CONSOLE_ARGS['highlighter']
 def add_cols_to_table(table: Table, col_names: list[str | dict]) -> None:
     """Left most col will be left justified, rest are center justified."""
     for i, col in enumerate(col_names):
+        justify='left' if i == 0 else 'center'
+
         if isinstance(col, dict):
             col_name = col['name']
             kwargs = col
             del kwargs['name']
+
+            if 'justify' in col:
+                justify = col['justify']
+                del col['justify']
         else:
             col_name = col
             kwargs = {}
 
-        table.add_column(col_name, justify='left' if i == 0 else 'center', **kwargs)
+        table.add_column(col_name, justify=justify, **kwargs)
 
 
 def build_highlighter(pattern: str) -> EpsteinHighlighter:
@@ -144,10 +153,9 @@ def parenthesize(msg: str | Text, style: str = '') -> Text:
 
 def print_author_panel(msg: str, color: str | None, footer: str | None = None) -> None:
     """Print a panel with the name of an emailer and a few tidbits of information about them."""
-    txt = Text(msg, justify='center')
-    color = color or 'white'
-    color = 'white' if color == DEFAULT else color
-    panel = Panel(txt, width=80, style=f"black on {color} bold")
+    color = 'white' if (not color or color == DEFAULT) else color
+    width = max(MIN_AUTHOR_PANEL_WIDTH, len(msg) + 4)
+    panel = Panel(Text(msg, justify='center'), width=width, style=f"black on {color} bold")
     console.print('\n', Align.center(panel))
 
     if footer:
@@ -181,16 +189,11 @@ def print_color_key() -> None:
 
 
 def print_title_page_header(epstein_files: 'EpsteinFiles') -> None:
-    not_optimized_msg = f"This page isn't optimized for mobile"
-
-    if not args.all_emails:
-        not_optimized_msg += f" but if you get past the header it should be readable"
-
-    console.print(f"{not_optimized_msg}.\n", style='dim')
     print_page_title(width=TITLE_WIDTH)
     site_type = EMAIL if (args.all_emails or args.email_timeline) else TEXT_MESSAGE
-    title = f"This is the " + ('chronological ' if args.email_timeline else '') + f"Epstein {site_type.title()}s page"
-    print_starred_header(title, num_spaces=4, num_stars=14)
+    title = f"This is the " + ('chronological ' if args.email_timeline else '') + f"Epstein {site_type.title()}s Page"
+    print_starred_header(title, num_spaces=9 if args.all_emails else 6, num_stars=14)
+    print_centered(f"These documents come from the Nov. 2025 House Oversight Committee release.\n", style='gray74')
     other_site_msg = "another page with" + (' all of' if other_site_type() == EMAIL else '')
     other_site_msg += f" Epstein's {other_site_type()}s also generated by this code"
 
@@ -218,8 +221,6 @@ def print_title_page_tables(epstein_files: 'EpsteinFiles') -> None:
 
 
 def print_json(label: str, obj: object, skip_falsey: bool = False) -> None:
-    print(obj)
-
     if isinstance(obj, dict):
         if skip_falsey:
             obj = {k: v for k, v in obj.items() if v}
@@ -232,68 +233,33 @@ def print_json(label: str, obj: object, skip_falsey: bool = False) -> None:
     console.line()
 
 
-def print_numbered_list_of_emailers(_list: list[str | None], epstein_files = None) -> None:
-    """Add the first emailed_at timestamp for each emailer if 'epstein_files' provided."""
-    current_year = 1990
-    current_year_month = current_year * 12
-    grey_idx = 0
-    console.line()
-
-    for i, name in enumerate(_list):
-        indent = '   ' if i < 9 else ('  ' if i < 99 else ' ')
-        txt = Text((indent) + F"   {i + 1}. ", style=DEFAULT_NAME_STYLE)
-
-        if epstein_files:
-            earliest_email_date = (epstein_files.earliest_email_at(name) or FALLBACK_TIMESTAMP).date()
-            year_months = (earliest_email_date.year * 12) + earliest_email_date.month
-
-            # Color year rollovers more brightly
-            if current_year != earliest_email_date.year:
-                grey_idx = 0
-            elif current_year_month != year_months:
-                grey_idx = ((current_year_month - 1) % 12) + 1
-
-            current_year_month = year_months
-            current_year = earliest_email_date.year
-            txt.append(escape(f"[{earliest_email_date}] "), style=f"grey{GREY_NUMBERS[grey_idx]}")
-
-        txt.append(highlighter(name or UNKNOWN))
-
-        if epstein_files:
-            num_days_in_converation = epstein_files.email_conversation_length_in_days(name)
-            msg = f" ({len(epstein_files.emails_for(name))} emails over {num_days_in_converation:,} days)"
-            txt.append(msg, style=f'dim italic')
-
-        console.print(txt)
-
-    console.line()
-
-
 def print_other_page_link(epstein_files: 'EpsteinFiles') -> None:
     markup_msg = link_markup(other_site_url(), 'the other page', style='light_slate_grey bold')
 
     if other_site_type() == EMAIL:
-        txt = Text.from_markup(markup_msg).append(f' is uncurated and has all {len(epstein_files.other_files)}')
-        txt.append(f" unclassifiable files and {len(epstein_files.emails):,} emails")
+        txt = Text.from_markup(markup_msg).append(f' is uncurated and has all {len(epstein_files.emails):,} emails')
+        txt.append(f" and {len(epstein_files.other_files)} unclassifiable files")
     else:
-        txt = Text.from_markup(markup_msg).append(f' displays only a small collection of emails and')
+        txt = Text.from_markup(markup_msg).append(f' displays a limited collection of emails and')
         txt.append(" unclassifiable files of particular interest")
 
-    print_centered(parenthesize(txt), style='dim')
+    print_centered(parenthesize(txt), style=OTHER_PAGE_MSG_STYLE)
     chrono_emails_markup = link_text_obj(CHRONOLOGICAL_EMAILS_URL, 'a page', style='light_slate_grey bold')
     chrono_emails_txt = Text(f"there's also ").append(chrono_emails_markup)
     chrono_emails_txt.append(' with a table of all the emails in chronological order')
-    print_centered(parenthesize(chrono_emails_txt), style='dim')
+    print_centered(parenthesize(chrono_emails_txt), style=OTHER_PAGE_MSG_STYLE)
 
 
 def print_page_title(expand: bool = True, width: int | None = None) -> None:
+    warning = f"This page was generated by {link_markup('https://pypi.org/project/rich/', 'rich')}."
+    print_centered(f"{warning} It is not optimized for mobile.", style='dim')
     title_panel = Panel(Text(PAGE_TITLE, justify='center'), expand=expand, style=TITLE_STYLE, width=width)
-    console.print(Align.center(vertically_pad(title_panel)))
+    print_centered(vertically_pad(title_panel))
     _print_social_media_links()
     console.line(2)
 
 
-def print_panel(msg: str, style: str = 'black on white', padding: tuple | None = None, centered: bool = False) -> None:
+def print_subtitle_panel(msg: str, style: str = 'black on white', padding: tuple | None = None, centered: bool = False) -> None:
     _padding: list[int] = list(padding or [0, 0, 0, 0])
     _padding[2] += 1  # Bottom pad
     actual_padding: tuple[int, int, int, int] = tuple(_padding)
@@ -308,7 +274,7 @@ def print_panel(msg: str, style: str = 'black on white', padding: tuple | None =
 def print_section_header(msg: str, style: str = SECTION_HEADER_STYLE, is_centered: bool = False) -> None:
     panel = Panel(Text(msg, justify='center'), expand=True, padding=(1, 1), style=style)
     panel = Align.center(panel) if is_centered else panel
-    console.print(Padding(panel, (3, 2, 1, 2)))
+    console.print(Padding(panel, (3, 0, 1, 0)))
 
 
 def print_starred_header(msg: str, num_stars: int = 7, num_spaces: int = 2, style: str = TITLE_STYLE) -> None:
@@ -340,8 +306,8 @@ def wrap_in_markup_style(msg: str, style: str | None = None) -> str:
     return msg
 
 
-def write_html(output_path: Path) -> None:
-    if not args.build:
+def write_html(output_path: Path | None) -> None:
+    if not output_path:
         logger.warning(f"Not writing HTML because args.build={args.build}.")
         return
 
@@ -393,5 +359,5 @@ def _print_social_media_links() -> None:
     print_centered(join_texts(social_links, join='  /  '))#, encloser='()'))#, encloser='‹›'))
 
 
-# if args.deep_debug:
-#     print_json('THEME_STYLES', THEME_STYLES)
+if args.colors_only:
+    print_json('THEME_STYLES', THEME_STYLES)

epstein_files/util/timer.py

@@ -11,7 +11,7 @@ class Timer:
     decimals: int = 2
 
     def print_at_checkpoint(self, msg: str) -> None:
-        logger.warning(f"{msg} in {self.seconds_since_checkpoint_str()}")
+        logger.warning(f"{msg} in {self.seconds_since_checkpoint_str()}...")
         self.checkpoint_at = time.perf_counter()
 
     def seconds_since_checkpoint_str(self) -> str:

epstein_files/util/word_count.py

@@ -17,7 +17,7 @@ from epstein_files.util.data import ALL_NAMES, flatten, sort_dict
 from epstein_files.util.env import args
 from epstein_files.util.logging import logger
 from epstein_files.util.rich import (console, highlighter, print_centered, print_color_key, print_page_title,
-     print_panel, print_starred_header, write_html)
+     print_subtitle_panel, print_starred_header, write_html)
 from epstein_files.util.search_result import MatchedLine, SearchResult
 from epstein_files.util.timer import Timer
 
@@ -196,7 +196,6 @@ def write_word_counts_html() -> None:
     epstein_files = EpsteinFiles.get_files(timer)
     email_subjects: set[str] = set()
     word_count = WordCount()
-
     # Remove dupes, junk mail, and fwded articles from emails
     emails = [e for e in epstein_files.non_duplicate_emails() if not (e.is_junk_mail() or e.is_fwded_article())]
 
@@ -225,7 +224,7 @@ def write_word_counts_html() -> None:
         for i, msg in enumerate(imessage_log.messages):
             if args.names and msg.author not in args.names:
                 continue
-            elif HTML_REGEX.search(line):
+            elif HTML_REGEX.search(msg.text):
                 continue
 
             for word in msg.text.split():
@@ -239,7 +238,7 @@ def write_word_counts_html() -> None:
     console.line()
     console.print(word_count)
     console.line(2)
-    print_panel(f"{len(COMMON_WORDS_LIST):,} Excluded Words", centered=True)
+    print_subtitle_panel(f"{len(COMMON_WORDS_LIST):,} Excluded Words", centered=True)
     console.print(', '.join(COMMON_WORDS_LIST), highlight=False)
     write_html(WORD_COUNT_HTML_PATH)
     timer.print_at_checkpoint(f"Finished counting words")

{epstein_files-1.1.0.dist-info → epstein_files-1.1.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: epstein-files
-Version: 1.1.0
+Version: 1.1.3
 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
@@ -81,6 +81,9 @@ epstein_diff 030999 020442
 ```
 
 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.
+
+The commands used to build the various sites that are deployed on Github Pages can be found in [`deploy.sh`](./deploy.sh).
+
 Run `epstein_generate --help` for command line option assistance.
 
 **Optional:** There are a handful of emails that I extracted from the legal filings they were contained in. If you want to include these files in your local analysis you'll need to copy those files from the repo into your local document directory. Something like: