epstein-files 1.1.5__py3-none-any.whl → 1.2.1__py3-none-any.whl

epstein_files/util/logging.py

@@ -33,7 +33,7 @@ LOG_LEVEL_ENV_VAR = 'LOG_LEVEL'
 # Augment the standard log highlighter with 'epstein_filename' matcher
 class LogHighlighter(ReprHighlighter):
     highlights = ReprHighlighter.highlights + [
-        *[fr"(?P<{doc_type}>{doc_type}(Cfg)?)" for doc_type in DOC_TYPE_STYLES.keys()],
+        *[fr"(?P<{doc_type}>{doc_type}(Cfg|s)?)" for doc_type in DOC_TYPE_STYLES.keys()],
         "(?P<epstein_filename>" + FILE_NAME_REGEX.pattern + ')',
     ]
 

epstein_files/util/output.py

@@ -1,28 +1,31 @@
 import json
+from os import unlink
+from typing import cast
 
 from rich.padding import Padding
 
 from epstein_files.documents.document import Document
-from epstein_files.documents.email import KRASSNER_RECIPIENTS, Email
+from epstein_files.documents.email import 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
+from epstein_files.person import Person
 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 DEFAULT_NAME_STYLE, TIMESTAMP_DIM, TIMESTAMP_STYLE
-from epstein_files.util.data import dict_sets_to_lists, sort_dict
+from epstein_files.util.constant.output_files import EMAILERS_TABLE_PNG_PATH, JSON_FILES_JSON_PATH, JSON_METADATA_PATH
+from epstein_files.util.constant.strings import AUTHOR, TIMESTAMP_STYLE
+from epstein_files.util.data import dict_sets_to_lists, uniquify
 from epstein_files.util.env import args
 from epstein_files.util.file_helper import log_file_write
-from epstein_files.util.highlighted_group import (JUNK_EMAILERS, QUESTION_MARKS_TXT, get_category_txt_for_name,
-     get_info_for_name, get_style_for_name, styled_name)
-from epstein_files.util.logging import logger
+from epstein_files.util.logging import logger, exit_with_error
 from epstein_files.util.rich import *
 
+DEVICE_SIGNATURE_SUBTITLE = f"Email [italic]Sent from \\[DEVICE][/italic] Signature Breakdown"
+DEVICE_SIGNATURE = 'Device Signature'
+DEVICE_SIGNATURE_PADDING = (1, 0)
 OTHER_INTERESTING_EMAILS_SUBTITLE = 'Other Interesting Emails\n(these emails have been flagged as being of particular interest)'
 PRINT_COLOR_KEY_EVERY_N_EMAILS = 150
-ALT_INFO_STYLE = 'medium_purple4'
 
 # Order matters. Default names to print emails for.
 DEFAULT_EMAILERS = [
@@ -58,20 +61,23 @@ INTERESTING_EMAIL_IDS = [
     '030630',  # 'What happens with zubair's project?'
     '033178',  # 'How is it going with Zubair?'
     '022396',  # Ukraine friend
-    # '023627',  # Michael Wolff article (already printed bc epstein->epstein email)
+    '026505',  # I know how dirty trump is
+    '029679',  # Trump's driver was the bag man
+    '030781', '026258', '026260',  # Bannon cripto coin issues
+    '023627',  # Michael Wolff article w/Brock
+    '032359',  # Jabor e-currency
+    #'023208',  # Extremely long Leon Black email chain
 ]
 
-INVALID_FOR_EPSTEIN_WEB = JUNK_EMAILERS + KRASSNER_RECIPIENTS + [
-    'ACT for America',
-    'BS Stern',
-    INTELLIGENCE_SQUARED,
-    UNKNOWN,
+INTERESTING_TEXT_IDS = [
+    '027275',  # "Crypto- Kerry- Qatar -sessions"
+    '027165',  # melaniee walker crypto health
 ]
 
 
 def print_email_timeline(epstein_files: EpsteinFiles) -> None:
     """Print a table of all emails in chronological order."""
-    emails = Document.sort_by_timestamp([e for e in epstein_files.non_duplicate_emails() if not e.is_junk_mail()])
+    emails = Document.sort_by_timestamp([e for e in epstein_files.non_duplicate_emails() if not e.is_mailing_list()])
     title = f'Table of All {len(emails):,} Non-Junk Emails in Chronological Order (actual emails below)'
     table = Email.build_emails_table(emails, title=title, show_length=True)
     console.print(Padding(table, (2, 0)))
@@ -82,30 +88,55 @@ def print_email_timeline(epstein_files: EpsteinFiles) -> None:
         console.print(email)
 
 
+def print_emailers_info(epstein_files: EpsteinFiles) -> None:
+    """Print tbe summary table of everyone in the files to an image."""
+    print_color_key()
+    console.line()
+    all_emailers = sorted(epstein_files.emailers(), key=lambda person: person.sort_key())
+    console.print(Person.emailer_info_table(all_emailers, show_epstein_total=True))
+
+    if not args.build:
+        logger.warning(f"Not writing .png file because --build is not set")
+        return
+
+    svg_path = f"{EMAILERS_TABLE_PNG_PATH}.svg"
+    console.save_svg(svg_path, theme=HTML_TERMINAL_THEME, title="Epstein Emailers")
+    log_file_write(svg_path)
+    import cairosvg
+    cairosvg.svg2png(url=svg_path, write_to=str(EMAILERS_TABLE_PNG_PATH))
+    log_file_write(EMAILERS_TABLE_PNG_PATH)
+    unlink(svg_path)
+
+
 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')
-    emailers_to_print: list[str | None]
-    already_printed_emails: list[Email] = []
+    all_emailers = sorted(epstein_files.emailers(), key=lambda person: person.earliest_email_at())
     num_emails_printed_since_last_color_key = 0
+    printed_emails: list[Email] = []
+    people_to_print: list[Person]
 
     if args.names:
-        emailers_to_print = args.names
+        try:
+            people_to_print = epstein_files.person_objs(args.names)
+        except Exception as e:
+            exit_with_error(str(e))
     else:
         if args.all_emails:
-            emailers_to_print = sorted(epstein_files.all_emailers(), key=lambda e: epstein_files.earliest_email_at(e))
+            people_to_print = all_emailers
         else:
-            emailers_to_print = DEFAULT_EMAILERS
+            people_to_print = epstein_files.person_objs(DEFAULT_EMAILERS)
 
         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)))
+        print_centered(Padding(Person.emailer_info_table(all_emailers, people_to_print), (2, 0, 1, 0)))
+
+    for person in people_to_print:
+        if person.name in epstein_files.uninteresting_emailers() and not args.names:
+            continue
 
-    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)
+        printed_person_emails = person.print_emails()
+        printed_emails.extend(printed_person_emails)
+        num_emails_printed_since_last_color_key += len(printed_person_emails)
 
         # Print color key every once in a while
         if num_emails_printed_since_last_color_key > PRINT_COLOR_KEY_EVERY_N_EMAILS:
@@ -113,26 +144,28 @@ def print_emails_section(epstein_files: EpsteinFiles) -> list[Email]:
             num_emails_printed_since_last_color_key = 0
 
     if args.names:
-        return already_printed_emails
+        return printed_emails
 
     # Print other interesting emails
-    already_printed_ids = [email.file_id for email in already_printed_emails]
-    extra_emails = [e for e in epstein_files.for_ids(INTERESTING_EMAIL_IDS) if e.file_id not in already_printed_ids]
-    print_subtitle_panel(OTHER_INTERESTING_EMAILS_SUBTITLE)
-    console.line()
+    printed_email_ids = [email.file_id for email in printed_emails]
+    extra_emails = [e for e in epstein_files.for_ids(INTERESTING_EMAIL_IDS) if e.file_id not in printed_email_ids]
 
-    for other_email in extra_emails:
-        console.print(other_email)
+    if len(extra_emails) > 0:
+        print_subtitle_panel(OTHER_INTERESTING_EMAILS_SUBTITLE)
+        console.line()
 
-    epstein_files.print_email_device_info()
+        for other_email in extra_emails:
+            console.print(other_email)
+            printed_emails.append(cast(Email, other_email))
 
     if args.all_emails:
-        _verify_all_emails_were_printed(epstein_files, already_printed_emails)
+        _verify_all_emails_were_printed(epstein_files, printed_emails)
 
-    fwded_articles = [e for e in already_printed_emails if e.config and e.is_fwded_article()]
-    log_msg = f"Rewrote {len(Email.rewritten_header_ids)} of {len(already_printed_emails)} email headers"
-    logger.warning(f"{log_msg}, {len(fwded_articles)} of the emails were forwarded articles.")
-    return already_printed_emails
+    _print_email_device_signature_info(epstein_files)
+    fwded_articles = [e for e in printed_emails if e.config and e.is_fwded_article()]
+    log_msg = f"Rewrote {len(Email.rewritten_header_ids)} of {len(printed_emails)} email headers"
+    logger.warning(f"  -> {log_msg}, {len(fwded_articles)} of the Emails printed were forwarded articles.")
+    return printed_emails
 
 
 def print_json_files(epstein_files: EpsteinFiles):
@@ -165,31 +198,39 @@ 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"MessengerLog Sender Counts", MessengerLog.count_authors(epstein_files.imessage_logs), skip_falsey=True)
-    print_json(f"Email Author Counts", epstein_files.email_author_counts, skip_falsey=True)
-    print_json(f"Email Recipient Counts", epstein_files.email_recipient_counts, skip_falsey=True)
+    print_json(f"Email Author Counts", epstein_files.email_author_counts(), skip_falsey=True)
+    print_json(f"Email 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("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("unknown_recipient_ids", epstein_files.unknown_recipient_ids())
     print_json("count_by_month", count_by_month(epstein_files.all_documents()))
 
 
-def print_other_files_section(files: list[OtherFile], epstein_files: EpsteinFiles) -> None:
+def print_other_files_section(epstein_files: EpsteinFiles) -> list[OtherFile]:
     """Returns the OtherFile objects that were interesting enough to print."""
+    if args.uninteresting:
+        files = [f for f in epstein_files.other_files if not f.is_interesting()]
+    else:
+        files = [f for f in epstein_files.other_files if args.all_other_files or f.is_interesting()]
+
     title_pfx = '' if args.all_other_files else 'Selected '
-    category_table = OtherFile.count_by_category_table(files, title_pfx=title_pfx)
+    category_table = OtherFile.summary_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)
+    return files
 
 
-def print_text_messages_section(imessage_logs: list[MessengerLog]) -> None:
+def print_text_messages_section(epstein_files: EpsteinFiles) -> list[MessengerLog]:
     """Print summary table and stats for text messages."""
+    imessage_logs = [log for log in epstein_files.imessage_logs if not args.names or log.author in args.names]
+
     if not imessage_logs:
-        logger.warning(f"No MessengerLog objects to output...")
-        return
+        logger.warning(f"No MessengerLogs found for {args.names}")
+        return imessage_logs
 
     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')
@@ -203,6 +244,8 @@ def print_text_messages_section(imessage_logs: list[MessengerLog]) -> None:
         console.print(Padding(log_file))
         console.line(2)
 
+    return imessage_logs
+
 
 def write_urls() -> None:
     """Write _URL style constant variables to URLS_ENV file so bash scripts can load as env vars."""
@@ -226,113 +269,26 @@ 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("Everyone Who Sent or Received an Email 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(include_useless=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)).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 name == JEFFREY_EPSTEIN:
-            info = Text('(emails sent by Epstein to himself that would not otherwise be printed)', style=ALT_INFO_STYLE)
-        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=ALT_INFO_STYLE)
-        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]}"),
-            styled_name(name, default_style='dim'),
-            category,
-            f"{len(epstein_files.emails_for(name)):,}",
-            info or '',
-        )
-
-    return table
+def _print_email_device_signature_info(epstein_files: EpsteinFiles) -> None:
+    print_subtitle_panel(DEVICE_SIGNATURE_SUBTITLE)
+    console.print(_signature_table(epstein_files.email_device_signatures_to_authors(), (DEVICE_SIGNATURE, AUTHOR), ', '))
+    console.print(_signature_table(epstein_files.email_authors_to_device_signatures(), (AUTHOR, DEVICE_SIGNATURE)))
+
+
+def _signature_table(keyed_sets: dict[str, set[str]], cols: tuple[str, str], join_char: str = '\n') -> Padding:
+    """Build table for who signed emails with 'Sent from my iPhone' etc."""
+    title = 'Email Signatures Used By Authors' if cols[0] == AUTHOR else 'Authors Seen Using Email Signatures'
+    table = build_table(title, header_style="bold reverse", show_lines=True)
+
+    for i, col in enumerate(cols):
+        table.add_column(col.title() + ('s' if i == 1 else ''))
+
+    new_dict = dict_sets_to_lists(keyed_sets)
+
+    for k in sorted(new_dict.keys()):
+        table.add_row(highlighter(k or UNKNOWN), highlighter(join_char.join(sorted(new_dict[k]))))
+
+    return Padding(table, DEVICE_SIGNATURE_PADDING)
 
 
 def _verify_all_emails_were_printed(epstein_files: EpsteinFiles, already_printed_emails: list[Email]) -> None:

epstein_files/util/rich.py

@@ -18,7 +18,7 @@ from epstein_files.util.constant.names import UNKNOWN
 from epstein_files.util.constant.strings import DEFAULT, EMAIL, NA, TEXT_MESSAGE
 from epstein_files.util.constant.urls import *
 from epstein_files.util.constants import HEADER_ABBREVIATIONS
-from epstein_files.util.data import json_safe, without_falsey
+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
@@ -26,11 +26,11 @@ from epstein_files.util.logging import logger
 
 TITLE_WIDTH = 50
 SUBTITLE_WIDTH = 110
-MIN_AUTHOR_PANEL_WIDTH = 80
 NUM_COLOR_KEY_COLS = 4
 NA_TXT = Text(NA, style='dim')
 SUBTITLE_PADDING = (2, 0, 1, 0)
 GREY_NUMBERS = [58, 39, 39, 35, 30, 27, 23, 23, 19, 19, 15, 15, 15]
+VALID_GREYS = [0, 3, 7, 11, 15, 19, 23, 27, 30, 35, 37, 39, 42, 46, 50, 53, 54, 58, 62, 63, 66, 69, 70, 74, 78, 82, 84, 85, 89, 93]
 
 INFO_STYLE = 'white dim italic'
 KEY_STYLE = 'honeydew2 bold'
@@ -70,7 +70,7 @@ CONSOLE_ARGS = {
     'color_system': '256',
     'highlighter': EpsteinHighlighter(),
     'record': args.build,
-    'safe_box': False,
+    'safe_box': True,
     'theme': Theme(THEME_STYLES),
     'width': args.width,
 }
@@ -83,21 +83,21 @@ console = Console(**CONSOLE_ARGS)
 highlighter = CONSOLE_ARGS['highlighter']
 
 
-def add_cols_to_table(table: Table, col_names: list[str | dict]) -> None:
+def add_cols_to_table(table: Table, cols: list[str | dict], justify: str = 'center') -> 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'
+    for i, col in enumerate(cols):
+        col_justify = 'left' if i == 0 else justify
 
         if isinstance(col, dict):
             col_name = col['name']
-            kwargs = deepcopy(col)
-            kwargs['justify'] = kwargs.get('justify', justify)
-            del kwargs['name']
+            col_kwargs = deepcopy(col)
+            col_kwargs['justify'] = col_kwargs.get('justify', col_justify)
+            del col_kwargs['name']
         else:
             col_name = col
-            kwargs = {'justify': justify}
+            col_kwargs = {'justify': col_justify}
 
-        table.add_column(col_name, **kwargs)
+        table.add_column(col_name, **col_kwargs)
 
 
 def build_highlighter(pattern: str) -> EpsteinHighlighter:
@@ -108,7 +108,7 @@ def build_highlighter(pattern: str) -> EpsteinHighlighter:
     return TempHighlighter()
 
 
-def build_table(title: str | None, cols: list[str | dict] | None = None, **kwargs) -> Table:
+def build_table(title: str | Text | None, cols: list[str | dict] | None = None, **kwargs) -> Table:
     table = Table(title=title, **{**DEFAULT_TABLE_KWARGS, **kwargs})
 
     if cols:
@@ -149,19 +149,6 @@ def parenthesize(msg: str | Text, style: str = '') -> Text:
     return Text('(', style=style).append(txt).append(')')
 
 
-def print_author_panel(msg: str, footer: str | None, style: str | None) -> None:
-    """Print a panel with the name of an emailer and a few tidbits of information about them."""
-    style = 'white' if (not style or style == DEFAULT) else style
-    panel_style = f"black on {style} bold"
-    width = max(MIN_AUTHOR_PANEL_WIDTH, len(msg) + 4, len(footer or '') + 8)
-    elements: list[RenderableType] = [Panel(Text(msg, justify='center'), width=width, style=panel_style)]
-
-    if footer:
-        elements.append(Text(f"({footer})", justify='center', style=f"{style} italic"))
-
-    print_centered(Padding(Group(*elements), (2, 0, 1, 0)))
-
-
 def print_centered(obj: RenderableType, style: str = '') -> None:
     console.print(Align.center(obj), style=style)
 
@@ -200,7 +187,7 @@ def print_title_page_header() -> None:
         Text.from_markup(link_markup(other_site_url(), other_site_msg, f"{OTHER_SITE_LINK_STYLE} bold")),
         link_text_obj(WORD_COUNT_URL, 'most frequently used words in the emails and texts', AUX_SITE_LINK_STYLE),
         link_text_obj(JSON_METADATA_URL, 'author attribution explanations', AUX_SITE_LINK_STYLE),
-        link_text_obj(WORD_COUNT_URL, "epstein's json files", AUX_SITE_LINK_STYLE),
+        link_text_obj(JSON_FILES_URL, "epstein's json files", AUX_SITE_LINK_STYLE),
     ]
 
     for link in links:
@@ -212,7 +199,8 @@ def print_title_page_tables(epstein_files: 'EpsteinFiles') -> None:
     _print_external_links()
     console.line()
     _print_abbreviations_table()
-    epstein_files.print_files_summary()
+    print_centered(epstein_files.overview_table())
+    console.line()
     print_color_key()
     print_centered(f"if you think there's an attribution error or can deanonymize an {UNKNOWN} contact {CRYPTADAMUS_TWITTER}", 'grey46')
     print_centered('note this site is based on the OCR text provided by Congress which is not always the greatest', 'grey23')
@@ -234,13 +222,11 @@ def print_json(label: str, obj: object, skip_falsey: bool = False) -> None:
 
 
 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.emails):,} emails')
+        txt = THE_OTHER_PAGE_TXT + Text(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 a limited collection of emails and')
+        txt = THE_OTHER_PAGE_TXT + (f' displays a limited collection of emails and')
         txt.append(" unclassifiable files of particular interest")
 
     print_centered(parenthesize(txt), style=OTHER_PAGE_MSG_STYLE)
@@ -267,7 +253,7 @@ def print_subtitle_panel(msg: str, style: str = 'black on white') -> 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, 0, 1, 0)))
+    console.print(Padding(panel, (3, 5, 1, 5)))
 
 
 def print_starred_header(msg: str, num_stars: int = 7, num_spaces: int = 2, style: str = TITLE_STYLE) -> None:
@@ -311,7 +297,7 @@ def write_html(output_path: Path | None) -> None:
 def _print_abbreviations_table() -> None:
     table = build_table(title="Abbreviations Used Frequently In These Conversations", show_header=False)
     table.add_column("Abbreviation", justify="center", style='bold')
-    table.add_column("Translation", style="white", justify="center")
+    table.add_column("Translation", justify="center", min_width=62, style="white")
 
     for k, v in HEADER_ABBREVIATIONS.items():
         table.add_row(highlighter(k), v)
@@ -326,8 +312,7 @@ def _print_external_links() -> None:
     raw_docs_link = join_texts([link_text_obj(RAW_OVERSIGHT_DOCS_GOOGLE_DRIVE_URL, 'raw files', style=f"{ARCHIVE_LINK_COLOR} dim")], encloser='()')
     print_centered(join_texts([presser_link, raw_docs_link]))
     print_centered(link_markup(JMAIL_URL, JMAIL) + " (read His Emails via Gmail interface)")
-    print_centered(link_markup(COFFEEZILLA_ARCHIVE_URL, 'Archive Of Epstein Materials') + " (Coffeezilla)")
-    print_centered(link_markup(COURIER_NEWSROOM_ARCHIVE_URL, 'Searchable Archive') + " (Courier Newsroom)")
+    print_centered(link_markup(EPSTEIN_DOCS_URL) + " (searchable archive)")
     print_centered(link_markup(EPSTEINIFY_URL) + " (raw document images)")
     print_centered(link_markup(EPSTEIN_WEB_URL) + " (character summaries)")
     print_centered(link_markup(EPSTEIN_MEDIA_URL) + " (raw document images)")

epstein_files/util/timer.py

@@ -1,5 +1,6 @@
 import time
 from dataclasses import dataclass, field
+from typing import Type
 
 from epstein_files.util.logging import logger
 
@@ -10,6 +11,19 @@ class Timer:
     checkpoint_at: float = field(default_factory=lambda: time.perf_counter())
     decimals: int = 2
 
+    def log_section_complete(self, label: str, all_docs: list, printed_docs: list) -> None:
+        num_skipped = len(all_docs) - len(printed_docs)
+        prefix = suffix = ''
+
+        if num_skipped == 0:
+            prefix = 'all '
+        elif num_skipped < 0:
+            suffix = f"(at least {num_skipped} {label}s printed more than once)"
+        else:
+            suffix = f"(skipped {num_skipped})"
+
+        self.print_at_checkpoint(f"Printed {prefix}{len(printed_docs)} {label}s {suffix}".strip())
+
     def print_at_checkpoint(self, msg: str) -> None:
         logger.warning(f"{msg} in {self.seconds_since_checkpoint_str()}...")
         self.checkpoint_at = time.perf_counter()

epstein_files/util/word_count.py

@@ -197,7 +197,7 @@ def write_word_counts_html() -> None:
     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())]
+    emails = [e for e in epstein_files.non_duplicate_emails() if not (e.is_mailing_list() or e.is_fwded_article())]
 
     for email in emails:
         if args.names and email.author not in args.names:

{epstein_files-1.1.5.dist-info → epstein_files-1.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: epstein-files
-Version: 1.1.5
+Version: 1.2.1
 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
@@ -17,6 +17,7 @@ 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: cairosvg (>=2.8.2,<3.0.0)
 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)
@@ -31,7 +32,7 @@ Project-URL: TextMessages, https://michelcrypt4d4mus.github.io/epstein_text_mess
 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
+# Color Highlighted Epstein Emails and Text Messages
 
 ![joi](https://github.com/michelcrypt4d4mus/epstein_text_messages/raw/master/docs/joi_ito_gavin_is_clever_epstein_funds_bitcoin_dev_team.png)
 
@@ -119,3 +120,6 @@ for file in epstein_files.other_files:
     do_stuff(file)
 ```
 
+# Everyone Who Sent or Received an Email in the November Document Dump
+![emails](https://github.com/michelcrypt4d4mus/epstein_text_messages/raw/master/docs/emailers_info_table.png)
+

epstein_files-1.2.1.dist-info/RECORD

@@ -0,0 +1,34 @@
+epstein_files/__init__.py,sha256=zhFnPc-TFQLJIO0qnXJzDM1Bf_u8nv308GDKAvn405g,4831
+epstein_files/documents/communication.py,sha256=QiCZ35R2ttlqcdovm5LBdGqgoj4xCcpl9ANqwlA9XGU,1752
+epstein_files/documents/document.py,sha256=YwWHaiccKpYiS4UJAiGzDviyYV2hzdeee_vdX4ybhOo,19519
+epstein_files/documents/email.py,sha256=xc2cv6KkMfKhNLMfqW6rmDDXn1ozRChao1i98-0byI8,42297
+epstein_files/documents/emails/email_header.py,sha256=3UD2pXMS9bRsFP4L5RSP2tSjI8OR6lq6gPKKao0DYLY,7739
+epstein_files/documents/imessage/text_message.py,sha256=IexwwVeF14FZqD7IuK47bIHYam07ZcD3rxheVNULNkc,3394
+epstein_files/documents/json_file.py,sha256=WcZW5NNqA67rHTdopbOGtup00muNaLlvrNgKb-K4zO8,1504
+epstein_files/documents/messenger_log.py,sha256=1bv62WoQMKR3gYDrK9W3Xm7cqLbKrkRBV7NTFL2cexE,7349
+epstein_files/documents/other_file.py,sha256=xZSILlnYlX2QIYCQCm6WNHvNqhF5do6AmxT7qxw-yog,9417
+epstein_files/epstein_files.py,sha256=D2yMCm1IM5Skojzvvlod6yTGI_nUtNQmwmX6dzv2Egs,14057
+epstein_files/person.py,sha256=pESfBu2VvsLtrA86V8_D2BHKtb4m0F4xCf7tIrwyp6c,13579
+epstein_files/util/constant/common_words.py,sha256=C1JERPnOGHV2UMC71aEue1i9QTQog-RfT3IzdcYQOYQ,3702
+epstein_files/util/constant/html.py,sha256=MFooFV8KfFBCm9hL1u6A3hi_u37i7lL6UKAYoKQj3PI,1505
+epstein_files/util/constant/names.py,sha256=pkS1BWBxpxveHRrL1Z4muaXcK2ICIwM7RFGCsCf7Qls,11267
+epstein_files/util/constant/output_files.py,sha256=gUZJ4mNoeJy3qTYWr_jhSmQI-_uV_jdLR0YCiaQd_Qg,1982
+epstein_files/util/constant/strings.py,sha256=z_vwWxWU-_85rDTbVyo8pbi-5keBYmYnbh758n2LebU,1989
+epstein_files/util/constant/urls.py,sha256=UvhQP6sWqZaNnkqXFIn44oVmYLWFA-A0FGpo40Ds-MM,5651
+epstein_files/util/constants.py,sha256=VdOOp1azsaFgeEEO9UMS8hx5NXNP4pozfyH2IA6kW9E,121794
+epstein_files/util/data.py,sha256=0kCGgs3Cscbn1Q9G82bSB51CKnQpz1iUzMJoBBM34IE,2964
+epstein_files/util/doc_cfg.py,sha256=gIBAoeheQYqqrCtVRU2ytYu799LyCiPxPyHDgWUad3c,9471
+epstein_files/util/env.py,sha256=bSf2PKkOukN7LA8YdrWQS7XTRY0pLTNXo8OiQ1EKJDE,6722
+epstein_files/util/file_helper.py,sha256=MpG1hI7DGs05fV9KSVb_ltc98DC8tv1E_TTo5X_E7Js,3010
+epstein_files/util/highlighted_group.py,sha256=8uuQAHIBk7c5VYzg2xqfHsR-TGKfX7f1qdwB74UfTfI,56719
+epstein_files/util/logging.py,sha256=pSLHGrUnPQGFMGYNIOTbZbCyy5dDOCbNrbNz22wIcZI,2099
+epstein_files/util/output.py,sha256=pqTu6MApTiRKc_Q0mZzKD73UAXnAbbA5zWzGijAH4OU,12681
+epstein_files/util/rich.py,sha256=z9wbvNQbOJqNWm7IDBNJFgRzMP2X5CTmOgwrOkuSEJk,13639
+epstein_files/util/search_result.py,sha256=1fxe0KPBQXBk4dLfu6m0QXIzYfZCzvaSkWqvghJGzxY,567
+epstein_files/util/timer.py,sha256=GZHefXiPA-prK-1szC1cebl44Y-i4Wd3K8zedFpcggg,1373
+epstein_files/util/word_count.py,sha256=rs-bsSMnGG1BnYUmxYuBLZ8X0-3-jJdaB03v1jOIq4g,9202
+epstein_files-1.2.1.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+epstein_files-1.2.1.dist-info/METADATA,sha256=_NTxSxgHoHb1uPeRlLqgxBl_9wJnyMsY2_3icXgZTDw,6222
+epstein_files-1.2.1.dist-info/WHEEL,sha256=d2fvjOD7sXsVzChCqf0Ty0JbHKBaLYwDbGQDwQTnJ50,88
+epstein_files-1.2.1.dist-info/entry_points.txt,sha256=5qYgwAXpxegeAicD_rzda_trDRnUC51F5UVDpcZ7j6Q,240
+epstein_files-1.2.1.dist-info/RECORD,,