epstein-files 1.0.11__py3-none-any.whl → 1.0.13__py3-none-any.whl

epstein_files/__init__.py

@@ -20,8 +20,8 @@ from epstein_files.util.constant.output_files import ALL_EMAILS_PATH, TEXT_MSGS_
 from epstein_files.util.env import args, specified_names
 from epstein_files.util.file_helper import coerce_file_path, extract_file_id
 from epstein_files.util.logging import logger
-from epstein_files.util.output import (print_emails, print_json_files, print_json_metadata, print_json_stats,
-     print_text_messages, write_urls)
+from epstein_files.util.output import (print_emails, print_json_files, print_json_stats,
+     print_text_messages, write_json_metadata, write_urls)
 from epstein_files.util.rich import build_highlighter, console, print_header, print_panel, write_html
 from epstein_files.util.timer import Timer
 from epstein_files.util.word_count import write_word_counts_html
@@ -37,7 +37,7 @@ def generate_html() -> None:
     epstein_files = EpsteinFiles.get_files(timer)
 
     if args.json_metadata:
-        print_json_metadata(epstein_files)
+        write_json_metadata(epstein_files)
         exit()
     elif args.json_files:
         print_json_files(epstein_files)

epstein_files/documents/communication.py

@@ -34,9 +34,9 @@ class Communication(Document):
     def is_attribution_uncertain(self) -> bool:
         return bool(self.config and self.config.is_attribution_uncertain)
 
-    def raw_document_link_txt(self, _style: str = '', include_alt_link: bool = True) -> Text:
+    def external_links(self, _style: str = '', include_alt_links: bool = True) -> Text:
         """Overrides super() method to apply self.author_style."""
-        return super().raw_document_link_txt(self.author_style, include_alt_link=include_alt_link)
+        return super().external_links(self.author_style, include_alt_links=include_alt_links)
 
     def summary(self) -> Text:
         return self._summary().append(CLOSE_PROPERTIES_CHAR)

epstein_files/documents/document.py

@@ -5,7 +5,7 @@ from dataclasses import asdict, dataclass, field
 from datetime import datetime
 from pathlib import Path
 from subprocess import run
-from typing import ClassVar, Sequence, TypeVar
+from typing import Callable, ClassVar, Sequence, TypeVar
 
 from rich.console import Console, ConsoleOptions, Group, RenderResult
 from rich.padding import Padding
@@ -16,8 +16,8 @@ from epstein_files.util.constant.names import *
 from epstein_files.util.constant.strings import *
 from epstein_files.util.constant.urls import *
 from epstein_files.util.constants import ALL_FILE_CONFIGS, FALLBACK_TIMESTAMP
-from epstein_files.util.data import collapse_newlines, date_str, iso_timestamp, patternize, without_falsey
-from epstein_files.util.doc_cfg import EmailCfg, DocCfg, Metadata, TextCfg
+from epstein_files.util.data import collapse_newlines, date_str, patternize, remove_zero_time_from_timestamp_str, without_falsey
+from epstein_files.util.doc_cfg import DUPE_TYPE_STRS, EmailCfg, DocCfg, Metadata, TextCfg
 from epstein_files.util.env import DOCS_DIR, args
 from epstein_files.util.file_helper import (file_stem_for_id, extract_file_id, file_size,
      file_size_str, is_local_extract_file)
@@ -31,10 +31,8 @@ INFO_INDENT = 2
 INFO_PADDING = (0, 0, 0, INFO_INDENT)
 MAX_TOP_LINES_LEN = 4000  # Only for logging
 MIN_DOCUMENT_ID = 10477
-LOCAL_EXTRACT_REGEX = re.compile(r"_\d$")
 WHITESPACE_REGEX = re.compile(r"\s{2,}|\t|\n", re.MULTILINE)
 
-EXTRACTED_FROM = 'Extracted from'
 MIN_TIMESTAMP = datetime(1991, 1, 1)
 MID_TIMESTAMP = datetime(2007, 1, 1)
 MAX_TIMESTAMP = datetime(2020, 1, 1)
@@ -96,15 +94,9 @@ class Document:
     def __post_init__(self):
         self.filename = self.file_path.name
         self.file_id = extract_file_id(self.filename)
-        self.config = deepcopy(ALL_FILE_CONFIGS.get(self.file_id))
+        self.config = self.config or deepcopy(ALL_FILE_CONFIGS.get(self.file_id))
 
-        if self.is_local_extract_file():
-            self.url_slug = LOCAL_EXTRACT_REGEX.sub('', file_stem_for_id(self.file_id))
-            extracted_from_doc_id = self.url_slug.split('_')[-1]
-
-            if extracted_from_doc_id in ALL_FILE_CONFIGS:
-                self._set_extract_config(deepcopy(ALL_FILE_CONFIGS[extracted_from_doc_id]))
-        else:
+        if 'url_slug' not in vars(self):
             self.url_slug = self.file_path.stem
 
         self._set_computed_fields(text=self.text or self._load_file())
@@ -122,28 +114,51 @@ class Document:
 
     def duplicate_file_txt(self) -> Text:
         """If the file is a dupe make a nice message to explain what file it's a duplicate of."""
-        if not self.config or not self.config.dupe_of_id:
+        if not self.config or not self.config.dupe_of_id or self.config.dupe_type is None:
             raise RuntimeError(f"duplicate_file_txt() called on {self.summary()} but not a dupe! config:\n\n{self.config}")
 
         txt = Text(f"Not showing ", style=INFO_STYLE).append(epstein_media_doc_link_txt(self.file_id, style='cyan'))
-        txt.append(f" because it's {self.config.duplicate_reason()} ")
+        txt.append(f" because it's {DUPE_TYPE_STRS[self.config.dupe_type]} ")
         return txt.append(epstein_media_doc_link_txt(self.config.dupe_of_id, style='royal_blue1'))
 
     def epsteinify_link(self, style: str = ARCHIVE_LINK_COLOR, link_txt: str | None = None) -> Text:
-        """Create a Text obj link to this document on epsteinify.com."""
-        return link_text_obj(epsteinify_doc_url(self.url_slug), link_txt or self.file_path.stem, style)
+        return self.external_url(epsteinify_doc_url, style, link_txt)
 
     def epstein_media_link(self, style: str = ARCHIVE_LINK_COLOR, link_txt: str | None = None) -> Text:
-        """Create a Text obj link to this document on epstein.media."""
-        return link_text_obj(epstein_media_doc_url(self.url_slug), link_txt or self.file_path.stem, style)
+        return self.external_url(epstein_media_doc_url, style, link_txt)
 
     def epstein_web_link(self, style: str = ARCHIVE_LINK_COLOR, link_txt: str | None = None) -> Text:
-        """Create a Text obj link to this document on EpsteinWeb."""
-        return link_text_obj(epstein_web_doc_url(self.url_slug), link_txt or self.file_path.stem, style)
+        return self.external_url(epstein_web_doc_url, style, link_txt)
+
+    def rollcall_link(self, style: str = ARCHIVE_LINK_COLOR, link_txt: str | None = None) -> Text:
+        return self.external_url(rollcall_doc_url, style, link_txt)
+
+    def external_url(self, fxn: Callable[[str], str], style: str = ARCHIVE_LINK_COLOR, link_txt: str | None = None) -> Text:
+        return link_text_obj(fxn(self.url_slug), link_txt or self.file_path.stem, style)
+
+    def external_links(self, style: str = '', include_alt_links: bool = False) -> Text:
+        """Returns colored links to epstein.media and and epsteinweb in a Text object."""
+        txt = Text('', style='white' if include_alt_links else ARCHIVE_LINK_COLOR)
+
+        if args.use_epstein_web:
+            txt.append(self.epstein_web_link(style=style))
+            alt_link = self.epstein_media_link(style='white dim', link_txt=EPSTEIN_MEDIA)
+        else:
+            txt.append(self.epstein_media_link(style=style))
+            alt_link = self.epstein_web_link(style='white dim', link_txt=EPSTEIN_WEB)
+
+        if include_alt_links:
+            txt.append(' (').append(self.epsteinify_link(style='white dim', link_txt=EPSTEINIFY)).append(')')
+            txt.append(' (').append(alt_link).append(')')
+
+            if self._class_name() == 'Email':
+                txt.append(' (').append(self.rollcall_link(style='white dim', link_txt=ROLLCALL)).append(')')
+
+        return txt
 
     def file_info_panel(self) -> Group:
         """Panel with filename linking to raw file plus any additional info about the file."""
-        panel = Panel(self.raw_document_link_txt(include_alt_link=True), border_style=self._border_style(), expand=False)
+        panel = Panel(self.external_links(include_alt_links=True), border_style=self._border_style(), expand=False)
         padded_info = [Padding(sentence, INFO_PADDING) for sentence in self.info()]
         return Group(*([panel] + padded_info))
 
@@ -155,12 +170,10 @@ class Document:
 
     def info(self) -> list[Text]:
         """0 to 2 sentences containing the info_txt() as well as any configured description."""
-        sentences = [
+        return without_falsey([
             self.info_txt(),
             highlighter(Text(self.config_description(), style=INFO_STYLE)) if self.config_description() else None
-        ]
-
-        return without_falsey(sentences)
+        ])
 
     def info_txt(self) -> Text | None:
         """Secondary info about this file (recipients, level of certainty, etc). Overload in subclasses."""
@@ -197,9 +210,9 @@ class Document:
 
         if self.is_local_extract_file():
             metadata['extracted_file'] = {
-                'explanation': 'This file was extracted from a court filing, not distributed directly. A copy can be found on github.',
-                'extracted_from_file': self.url_slug + '.txt',
-                'extracted_file_url': extracted_file_url(self.filename),
+                'explanation': 'Manually extracted from one of the court filings.',
+                'extracted_from': self.url_slug + '.txt',
+                'url': extracted_file_url(self.filename),
             }
 
         return metadata
@@ -208,25 +221,6 @@ class Document:
         with open(self.file_path) as f:
             return f.read()
 
-    def raw_document_link_txt(self, style: str = '', include_alt_link: bool = False) -> Text:
-        """Returns colored links to epstein.media and and epsteinweb in a Text object."""
-        txt = Text('', style='white' if include_alt_link else ARCHIVE_LINK_COLOR)
-
-        if args.use_epstein_web:
-            txt.append(self.epstein_web_link(style=style))
-
-            if include_alt_link:
-                txt.append(' (').append(self.epsteinify_link(style='white dim', link_txt=EPSTEINIFY)).append(')')
-                txt.append(' (').append(self.epstein_media_link(style='white dim', link_txt=EPSTEIN_MEDIA)).append(')')
-        else:
-            txt.append(self.epstein_media_link(style=style))
-
-            if include_alt_link:
-                txt.append(' (').append(self.epsteinify_link(style='white dim', link_txt=EPSTEINIFY)).append(')')
-                txt.append(' (').append(self.epstein_web_link(style='white dim', link_txt=EPSTEIN_WEB)).append(')')
-
-        return txt
-
     def repair_ocr_text(self, repairs: dict[str | re.Pattern, str], text: str) -> str:
         """Apply a dict of repairs (key is pattern or string, value is replacement string) to text."""
         for k, v in repairs.items():
@@ -253,7 +247,7 @@ class Document:
         txt.append(f" {self.url_slug}", style=FILENAME_STYLE)
 
         if self.timestamp:
-            timestamp_str = iso_timestamp(self.timestamp).removesuffix(' 00:00:00')
+            timestamp_str = remove_zero_time_from_timestamp_str(self.timestamp).replace('T', ' ')
             txt.append(' (', style=SYMBOL_STYLE)
             txt.append(f"{timestamp_str}", style=TIMESTAMP_DIM).append(')', style=SYMBOL_STYLE)
 
@@ -327,26 +321,6 @@ class Document:
         self.lines = [line.strip() if self.strip_whitespace else line for line in self.text.split('\n')]
         self.num_lines = len(self.lines)
 
-    def _set_extract_config(self, doc_cfg: DocCfg | EmailCfg) -> None:
-        """Copy info from original config for file this document was extracted from."""
-        if self.config:
-            self.warn(f"Merging existing config with config for file this document was extracted from")
-        else:
-            self.config = EmailCfg(id=self.file_id)
-
-        extracted_from_description = doc_cfg.complete_description()
-
-        if extracted_from_description:
-            extracted_description = f"{EXTRACTED_FROM} {extracted_from_description}"
-
-            if self.config.description:
-                self.warn(f"Overwriting description '{self.config.description}' with extract description '{doc_cfg.description}'")
-
-            self.config.description = extracted_description
-
-        self.config.is_interesting = self.config.is_interesting or doc_cfg.is_interesting
-        self.warn(f"Constructed local config\n{self.config}")
-
     def _write_clean_text(self, output_path: Path) -> None:
         """Write self.text to 'output_path'. Used only for diffing files."""
         if output_path.exists():

epstein_files/documents/email.py

@@ -1,5 +1,6 @@
 import logging
 import re
+from copy import deepcopy
 from dataclasses import asdict, dataclass, field
 from datetime import datetime
 from typing import ClassVar, cast
@@ -21,6 +22,7 @@ from epstein_files.util.constants import *
 from epstein_files.util.data import (TIMEZONE_INFO, collapse_newlines, escape_single_quotes, extract_last_name,
      flatten, remove_timezone, uniquify)
 from epstein_files.util.doc_cfg import EmailCfg, Metadata
+from epstein_files.util.file_helper import extract_file_id, file_stem_for_id
 from epstein_files.util.highlighted_group import get_style_for_name
 from epstein_files.util.logging import logger
 from epstein_files.util.rich import *
@@ -35,9 +37,11 @@ REPLY_TEXT_REGEX = re.compile(rf"^(.*?){REPLY_LINE_PATTERN}", re.DOTALL | re.IGN
 BAD_TIMEZONE_REGEX = re.compile(fr'\((UTC|GMT\+\d\d:\d\d)\)|{REDACTED}')
 DATE_HEADER_REGEX = re.compile(r'(?:Date|Sent):? +(?!by|from|to|via)([^\n]{6,})\n')
 TIMESTAMP_LINE_REGEX = re.compile(r"\d+:\d+")
+LOCAL_EXTRACT_REGEX = re.compile(r"_\d$")
 
 SUPPRESS_LOGS_FOR_AUTHORS = ['Undisclosed recipients:', 'undisclosed-recipients:', 'Multiple Senders Multiple Senders']
 REWRITTEN_HEADER_MSG = "(janky OCR header fields were prettified, check source if something seems off)"
+APPEARS_IN = 'Appears in'
 MAX_CHARS_TO_PRINT = 4000
 MAX_NUM_HEADER_LINES = 14
 MAX_QUOTED_REPLIES = 2
@@ -128,7 +132,6 @@ JUNK_EMAILERS = [
     'How To Academy',
     'Jokeland',
     JP_MORGAN_USGIO,
-    'Saved by Internet Explorer 11',
 ]
 
 MAILING_LISTS = [
@@ -248,6 +251,7 @@ KRASSNER_RECIPIENTS = uniquify(flatten([ALL_FILE_CONFIGS[id].recipients for id i
 
 # No point in ever displaying these; their emails show up elsewhere because they're mostly CC recipients
 USELESS_EMAILERS = FLIGHT_IN_2012_PEOPLE + IRAN_DEAL_RECIPIENTS + KRASSNER_RECIPIENTS + [
+    'Alan Dlugash',                            # CCed with Richard Kahn
     'Alan Rogers',                           # Random CC
     'Andrew Friendly',                       # Presumably some relation of Kelly Friendly
     'BS Stern',                              # A random fwd of email we have
@@ -264,14 +268,14 @@ USELESS_EMAILERS = FLIGHT_IN_2012_PEOPLE + IRAN_DEAL_RECIPIENTS + KRASSNER_RECIP
     'Lyn Fontanilla',                        # Random CC
     'Mark Albert',                           # Random CC
     'Matthew Schafer',                       # Random CC
+    MICHAEL_BUCHHOLTZ,                       # Terry Kafka CC
+    'Nancy Dahl',                            # covered by Lawrence Krauss (her husband)
     'Michael Simmons',                       # Random CC
     'Nancy Portland',                        # Lawrence Krauss CC
     'Oliver Goodenough',                     # Robert Trivers CC
-    'Owen Blicksilver',                      # Landon Thomas CC
     'Peter Aldhous',                         # Lawrence Krauss CC
     'Sam Harris',                            # Lawrence Krauss CC
     SAMUEL_LEFF,                             # Random CC
-    "Saved by Internet Explorer 11",
     'Sean T Lehane',                         # Random CC
     'Stephen Rubin',                         # Random CC
     'Tim Kane',                              # Random CC
@@ -318,6 +322,17 @@ class Email(Communication):
     rewritten_header_ids: ClassVar[set[str]] = set([])
 
     def __post_init__(self):
+        self.filename = self.file_path.name
+        self.file_id = extract_file_id(self.filename)
+
+        # Special handling for copying properties out of the config for the document this one was extracted from
+        if self.is_local_extract_file():
+            self.url_slug = LOCAL_EXTRACT_REGEX.sub('', file_stem_for_id(self.file_id))
+            extracted_from_doc_id = self.url_slug.split('_')[-1]
+
+            if extracted_from_doc_id in ALL_FILE_CONFIGS:
+                self._set_config_for_extracted_file(ALL_FILE_CONFIGS[extracted_from_doc_id])
+
         super().__post_init__()
 
         try:
@@ -340,8 +355,12 @@ class Email(Communication):
         self.actual_text = self._actual_text()
         self.sent_from_device = self._sent_from_device()
 
+    def attachments(self) -> list[str]:
+        return (self.header.attachments or '').split(';')
+
     def info_txt(self) -> Text:
-        txt = Text("OCR text of email from ", style='grey46').append(self.author_txt).append(' to ')
+        email_type = 'fwded article' if self.is_fwded_article() else 'email'
+        txt = Text(f"OCR text of {email_type} from ", style='grey46').append(self.author_txt).append(' to ')
         return txt.append(self._recipients_txt()).append(highlighter(f" probably sent at {self.timestamp}"))
 
     def is_fwded_article(self) -> bool:
@@ -566,11 +585,11 @@ class Email(Communication):
                 self._merge_lines(2, 5)
             elif self.file_id in ['029498', '031428']:
                 self._merge_lines(2, 4)
-        elif self.file_id in ['029976', '023067']:
+        elif self.file_id in ['029976', '023067', '033576']:
             self._merge_lines(3)  # Merge 4th and 5th rows
         elif self.file_id in '026609 029402 032405 022695'.split():
             self._merge_lines(4)  # Merge 5th and 6th rows
-        elif self.file_id in ['019407', '031980', '030384', '033144', '030999', '033575', '029835', '030381']:
+        elif self.file_id in ['019407', '031980', '030384', '033144', '030999', '033575', '029835', '030381', '033357']:
             self._merge_lines(2, 4)
         elif self.file_id in ['029154', '029163']:
             self._merge_lines(2, 5)
@@ -591,6 +610,8 @@ class Email(Communication):
             self._merge_lines(7, 9)
         elif self.file_id == '030299':
             self._merge_lines(7, 10)
+        elif self.file_id in ['022673', '022684']:
+            self._merge_lines(9)
         elif self.file_id == '014860':
             self._merge_lines(3)
             self._merge_lines(4)
@@ -649,6 +670,27 @@ class Email(Communication):
             sent_from = sent_from_match.group(0)
             return 'S' + sent_from[1:] if sent_from.startswith('sent') else sent_from
 
+    def _set_config_for_extracted_file(self, extracted_from_doc_cfg: DocCfg) -> None:
+        """Copy info from original config for file this document was extracted from."""
+        if self.file_id in ALL_FILE_CONFIGS:
+            self.config = cast(EmailCfg, deepcopy(ALL_FILE_CONFIGS[self.file_id]))
+            self.warn(f"Merging existing config for {self.file_id} with config for file this document was extracted from")
+        else:
+            self.config = EmailCfg(id=self.file_id)
+
+        extracted_from_description = extracted_from_doc_cfg.complete_description()
+
+        if extracted_from_description:
+            extracted_description = f"{APPEARS_IN} {extracted_from_description}"
+
+            if self.config.description:
+                self.warn(f"Overwriting description '{self.config.description}' with extract description '{self.config.description}'")
+
+            self.config.description = extracted_description
+
+        self.config.is_interesting = self.config.is_interesting or extracted_from_doc_cfg.is_interesting
+        self.warn(f"Constructed synthetic config: {self.config}")
+
     def __rich_console__(self, console: Console, options: ConsoleOptions) -> RenderResult:
         logger.debug(f"Printing '{self.filename}'...")
         yield self.file_info_panel()

epstein_files/documents/imessage/text_message.py

@@ -45,7 +45,7 @@ class TextMessage:
             self.author_str = self.author_str or self.author
 
         if not self.id_confirmed and self.author is not None and self.author != JEFFREY_EPSTEIN:
-            self.author_str = self.author + ' (?)'
+            self.author_str += ' (?)'
 
     def timestamp(self) -> datetime:
         return datetime.strptime(self.timestamp_str, MSG_DATE_FORMAT)

epstein_files/documents/json_file.py

@@ -39,7 +39,7 @@ class JsonFile(OtherFile):
         return JSON
 
     def info_txt(self) -> Text | None:
-        return Text(f"JSON file, seems to contain link unfurl/embed data for iMessage or similar", style=INFO_STYLE)
+        return Text(f"JSON file, contains preview data for links sent a messaging app", style=INFO_STYLE)
 
     def is_interesting(self):
         return False

epstein_files/documents/messenger_log.py

@@ -16,7 +16,7 @@ from epstein_files.util.data import iso_timestamp, listify, sort_dict
 from epstein_files.util.doc_cfg import Metadata, TextCfg
 from epstein_files.util.highlighted_group import get_style_for_name
 from epstein_files.util.logging import logger
-from epstein_files.util.rich import build_table, highlighter
+from epstein_files.util.rich import LAST_TIMESTAMP_STYLE, build_table, highlighter
 
 CONFIRMED_MSG = 'Found confirmed counterparty'
 GUESSED_MSG = 'This is probably a conversation with'
@@ -76,7 +76,7 @@ class MessengerLog(Communication):
         is_phone_number = author_str.startswith('+')
 
         if is_phone_number:
-            logger.warning(f"{self.summary()} Found phone number: {author_str}")
+            logger.info(f"{self.summary()} Found phone number: {author_str}")
             self.phone_number = author_str
 
         # If the Sender: is redacted or if it's an unredacted phone number that means it's from self.author
@@ -130,7 +130,7 @@ class MessengerLog(Communication):
         counts_table.add_column('Files', justify='right', style='white')
         counts_table.add_column("Msgs", justify='right')
         counts_table.add_column('First Sent At', justify='center', highlight=True, width=21)
-        counts_table.add_column('Last Sent At', justify='center', style='wheat4', width=21)
+        counts_table.add_column('Last Sent At', justify='center', style=LAST_TIMESTAMP_STYLE, width=21)
         counts_table.add_column('Days', justify='right', style='dim')
 
         for name, count in sort_dict(cls.count_authors(imessage_logs)):

epstein_files/documents/other_file.py

@@ -107,7 +107,7 @@ UNINTERESTING_PREFIXES = FINANCIAL_REPORTS_AUTHORS + [
     TEXT_OF_US_LAW,
     TRANSLATION,
     TWEET,
-    THE_REAL_DEAL_ARTICLE,
+    REAL_DEAL_ARTICLE,
     TRUMP_DISCLOSURES,
     UBS_CIO_REPORT,
     UN_GENERAL_ASSEMBLY,
@@ -240,7 +240,7 @@ class OtherFile(Document):
         table.add_column(FIRST_FEW_LINES, justify='left', style='pale_turquoise4')
 
         for file in files:
-            link_and_info = [file.raw_document_link_txt()]
+            link_and_info = [file.external_links()]
             date_str = file.date_str()
 
             if file.is_duplicate():

epstein_files/epstein_files.py

@@ -23,12 +23,12 @@ from epstein_files.util.constant.strings import *
 from epstein_files.util.constant.urls import (EPSTEIN_MEDIA, EPSTEIN_WEB, JMAIL, epstein_media_person_url,
      epsteinify_name_url, epstein_web_person_url, search_jmail_url, search_twitter_url)
 from epstein_files.util.constants import *
-from epstein_files.util.data import dict_sets_to_lists, json_safe, listify, sort_dict
+from epstein_files.util.data import dict_sets_to_lists, iso_timestamp, json_safe, listify, sort_dict
 from epstein_files.util.doc_cfg import EmailCfg, Metadata
 from epstein_files.util.env import DOCS_DIR, args, logger
 from epstein_files.util.file_helper import file_size_str
 from epstein_files.util.highlighted_group import get_info_for_name, get_style_for_name
-from epstein_files.util.rich import (DEFAULT_NAME_STYLE, NA_TXT, add_cols_to_table,
+from epstein_files.util.rich import (DEFAULT_NAME_STYLE, LAST_TIMESTAMP_STYLE, NA_TXT, add_cols_to_table,
      build_table, console, highlighter, link_text_obj, link_markup, print_author_header, print_centered,
      print_other_site_link, print_panel, print_section_header, vertically_pad)
 from epstein_files.util.search_result import SearchResult
@@ -278,25 +278,40 @@ class EpsteinFiles:
     def print_emailer_counts_table(self) -> None:
         footer = f"Identified authors of {self.attributed_email_count():,} out of {len(self.emails):,} emails ."
         counts_table = build_table("Email Counts", caption=footer)
-        add_cols_to_table(counts_table, ['Name', 'Count', 'Sent', "Recv'd", JMAIL, EPSTEIN_MEDIA, EPSTEIN_WEB, 'Twitter'])
+
+        add_cols_to_table(counts_table, [
+            'Name',
+            'Num',
+            'Sent',
+            "Recv",
+            {'name': 'First', 'highlight': True},
+            {'name': 'Last', 'style': LAST_TIMESTAMP_STYLE},
+            JMAIL,
+            'eMedia',
+            'eWeb',
+            'Twitter',
+        ])
 
         emailer_counts = {
             emailer: self.email_author_counts[emailer] + self.email_recipient_counts[emailer]
             for emailer in self.all_emailers(True)
         }
 
-        for p, count in sort_dict(emailer_counts):
-            style = get_style_for_name(p, default_style=DEFAULT_NAME_STYLE)
+        for name, count in sort_dict(emailer_counts):
+            style = get_style_for_name(name, default_style=DEFAULT_NAME_STYLE)
+            emails = self.emails_for(name)
 
             counts_table.add_row(
-                Text.from_markup(link_markup(epsteinify_name_url(p or UNKNOWN), p or UNKNOWN, style)),
+                Text.from_markup(link_markup(epsteinify_name_url(name or UNKNOWN), name or UNKNOWN, style)),
                 str(count),
-                str(self.email_author_counts[p]),
-                str(self.email_recipient_counts[p]),
-                '' if p is None else link_text_obj(search_jmail_url(p), JMAIL),
-                '' if not is_ok_for_epstein_web(p) else link_text_obj(epstein_media_person_url(p), EPSTEIN_MEDIA),
-                '' if not is_ok_for_epstein_web(p) else link_text_obj(epstein_web_person_url(p), EPSTEIN_WEB),
-                '' if p is None else link_text_obj(search_twitter_url(p), 'search X'),
+                str(self.email_author_counts[name]),
+                str(self.email_recipient_counts[name]),
+                emails[0].timestamp_without_seconds(),
+                emails[-1].timestamp_without_seconds(),
+                '' if name is None else link_text_obj(search_jmail_url(name), JMAIL),
+                '' if not is_ok_for_epstein_web(name) else link_text_obj(epstein_media_person_url(name), 'eMedia'),
+                '' if not is_ok_for_epstein_web(name) else link_text_obj(epstein_web_person_url(name), 'eWeb'),
+                '' if name is None else link_text_obj(search_twitter_url(name), 'search X'),
             )
 
         console.print(vertically_pad(counts_table, 2))

epstein_files/util/constant/names.py

@@ -42,6 +42,7 @@ CECILE_DE_JONGH = 'Cecile de Jongh'
 CECILIA_STEEN = 'Cecilia Steen'
 CELINA_DUBIN = 'Celina Dubin'
 CHRISTINA_GALBRAITH = 'Christina Galbraith'  # Works with Tyler Shears on reputation stuff
+DANGENE_AND_JENNIE_ENTERPRISE = 'Dangene and Jennie Enterprise'
 DANIEL_SABBA = 'Daniel Sabba'
 DANIEL_SIAD = 'Daniel Siad'
 DANNY_FROST = 'Danny Frost'
@@ -143,7 +144,7 @@ REID_HOFFMAN = 'Reid Hoffman'
 REID_WEINGARTEN = 'Reid Weingarten'
 RENATA_BOLOTOVA = 'Renata Bolotova'
 RICHARD_KAHN = 'Richard Kahn'
-ROBERT_D_CRITTON = 'Robert D. Critton Jr.'
+ROBERT_D_CRITTON_JR = 'Robert D. Critton Jr.'
 ROBERT_LAWRENCE_KUHN = 'Robert Lawrence Kuhn'
 ROBERT_TRIVERS = 'Robert Trivers'
 ROGER_SCHANK = 'Roger Schank'
@@ -178,6 +179,7 @@ JARED_KUSHNER = 'Jared Kushner'
 JULIE_K_BROWN = 'Julie K. Brown'
 KARIM_SADJADPOUR = 'KARIM SADJADPOUR'.title()
 MICHAEL_J_BOCCIO = 'Michael J. Boccio'
+NERIO_ALESSANDRI = 'Nerio Alessandri (Founder and Chairman of Technogym S.p.A. Italy)'
 PAUL_G_CASSELL = 'Paul G. Cassell'
 RUDY_GIULIANI = 'Rudy Giuliani'
 TULSI_GABBARD = 'Tulsi Gabbard'
@@ -226,22 +228,23 @@ NAMES_TO_NOT_HIGHLIGHT: list[str] = [name.lower() for name in [
 # Names to color white in the word counts
 OTHER_NAMES = NAMES_TO_NOT_HIGHLIGHT + """
     aaron albert alberto alec alexandra alice anderson andre ann anna anne ariana arthur
-    baldwin barack ben benjamin berger bert binant bob bonner boyden bradley brady branson bruno bryant burton
+    baldwin barack ben benjamin berger bert binant bob bonner boyden bradley brady branson bright bruno bryant burton
     chapman charles charlie christopher clint cohen colin collins conway
-    davis dean debra deborah dennis diana diane diaz dickinson dixon dominique don dylan
+    danny davis dean debra deborah dennis diana diane diaz dickinson dixon dominique don dylan
     edmond elizabeth emily entwistle erik evelyn
-    ferguson flachsbart francis franco frank
+    ferguson flachsbart francis franco frank frost
     gardner gary geoff geoffrey gilbert gloria goldberg gonzalez gould graham greene guarino gwyneth
-    hancock harold harrison harry helen hirsch hofstadter horowitz hussein
+    hancock harold harrison harry hay helen hill hirsch hofstadter horowitz hussein
     ian isaac isaacson
-    jamie jane janet jason jen jim joe johnson jones josh julie justin
+    james jamie jane janet jason jen jim joe johnson jones josh julie justin
     karl kate kathy kelly kim kruger kyle
-    leo leonard lenny leslie lieberman louis lynch lynn
+    laurie leo leonard lenny leslie lieberman louis lynch lynn
     marcus marianne matt matthew melissa michele michelle moore moscowitz
-    nicole nussbaum
+    nancy nicole nussbaum
+    owen
     paulson philippe
     rafael ray richard richardson rob robin ron rubin rudolph ryan
-    sara sarah seligman serge sergey silverman sloman smith snowden sorkin steele stevie stewart
+    sara sarah sean seligman serge sergey silverman sloman smith snowden sorkin steele stevie stewart
     ted theresa thompson tiffany timothy tony
     valeria
     walter warren weinstein weiss william

epstein_files/util/constant/strings.py

@@ -20,7 +20,7 @@ POLITICS = 'politics'
 PROPERTY = 'property'
 PUBLICIST = 'publicist'
 REPUTATION = 'reputation'
-SKYPE_LOG= 'skype log'
+SKYPE_LOG = 'Skype log'
 SOCIAL = 'social'
 SPEECH = 'speech'
 
@@ -39,6 +39,7 @@ MIAMI_HERALD = 'Miami Herald'
 NYT = "New York Times"
 PALM_BEACH_DAILY_NEWS = f'{PALM_BEACH} Daily News'
 PALM_BEACH_POST = f'{PALM_BEACH} Post'
+SHIMON_POST = 'The Shimon Post'
 THE_REAL_DEAL = 'The Real Deal'
 WAPO = 'WaPo'
 VI_DAILY_NEWS = f'{VIRGIN_ISLANDS} Daily News'

epstein_files/util/constant/urls.py

@@ -13,11 +13,12 @@ ARCHIVE_LINK_COLOR = 'slate_blue3'
 TEXT_LINK = 'text_link'
 
 # External site names
-ExternalSite = Literal['epstein.media', 'epsteinify', 'EpsteinWeb']
+ExternalSite = Literal['epstein.media', 'epsteinify', 'EpsteinWeb', 'RollCall']
 EPSTEIN_MEDIA = 'epstein.media'
 EPSTEIN_WEB = 'EpsteinWeb'
 EPSTEINIFY = 'epsteinify'
 JMAIL = 'Jmail'
+ROLLCALL = 'RollCall'
 
 GH_PROJECT_URL = 'https://github.com/michelcrypt4d4mus/epstein_text_messages'
 GH_MASTER_URL = f"{GH_PROJECT_URL}/blob/master"
@@ -41,9 +42,10 @@ EPSTEIN_WEB_URL = 'https://epsteinweb.org'
 JMAIL_URL = 'https://jmail.world'
 
 DOC_LINK_BASE_URLS: dict[ExternalSite, str] = {
-    EPSTEIN_MEDIA: f"{EPSTEIN_MEDIA_URL}/files",
-    EPSTEIN_WEB: f'{EPSTEIN_WEB_URL}/wp-content/uploads/epstein_evidence/images',
-    EPSTEINIFY: f"{EPSTEINIFY_URL}/document",
+    EPSTEIN_MEDIA: f"{EPSTEIN_MEDIA_URL}/files/",
+    EPSTEIN_WEB: f'{EPSTEIN_WEB_URL}/wp-content/uploads/epstein_evidence/images/',
+    EPSTEINIFY: f"{EPSTEINIFY_URL}/document/",
+    ROLLCALL: f'https://rollcall.com/factbase/epstein/file?id=',
 }
 
 
@@ -53,7 +55,7 @@ epsteinify_doc_link_txt = lambda filename_or_id, style = TEXT_LINK: Text.from_ma
 epsteinify_doc_url = lambda file_stem: build_doc_url(DOC_LINK_BASE_URLS[EPSTEINIFY], file_stem)
 epsteinify_name_url = lambda name: f"{EPSTEINIFY_URL}/?name={urllib.parse.quote(name)}"
 
-epstein_media_doc_url = lambda file_stem: build_doc_url(DOC_LINK_BASE_URLS[EPSTEIN_MEDIA], file_stem, True)
+epstein_media_doc_url = lambda file_stem: build_doc_url(DOC_LINK_BASE_URLS[EPSTEIN_MEDIA], file_stem, 'lower')
 epstein_media_doc_link_markup = lambda filename_or_id, style = TEXT_LINK: external_doc_link_markup(EPSTEIN_MEDIA, filename_or_id, style)
 epstein_media_doc_link_txt = lambda filename_or_id, style = TEXT_LINK: Text.from_markup(epstein_media_doc_link_markup(filename_or_id, style))
 epstein_media_person_url = lambda person: f"{EPSTEIN_MEDIA_URL}/people/{parameterize(person)}"
@@ -62,16 +64,19 @@ epstein_web_doc_url = lambda file_stem: f"{DOC_LINK_BASE_URLS[EPSTEIN_WEB]}/{fil
 epstein_web_person_url = lambda person: f"{EPSTEIN_WEB_URL}/{parameterize(person)}"
 epstein_web_search_url = lambda s: f"{EPSTEIN_WEB_URL}/?ewmfileq={urllib.parse.quote(s)}&ewmfilepp=20"
 
+rollcall_doc_url = lambda file_stem: build_doc_url(DOC_LINK_BASE_URLS[ROLLCALL], file_stem, 'title')
+
 search_archive_url = lambda txt: f"{COURIER_NEWSROOM_ARCHIVE_URL}&q={urllib.parse.quote(txt)}&p=1"
 search_coffeezilla_url = lambda txt: f"{COFFEEZILLA_ARCHIVE_URL}&q={urllib.parse.quote(txt)}&p=1"
 search_jmail_url = lambda txt: f"{JMAIL_URL}/search?q={urllib.parse.quote(txt)}"
 search_twitter_url = lambda txt: f"https://x.com/search?q={urllib.parse.quote(txt)}&src=typed_query&f=live"
 
 
-def build_doc_url(base_url: str, filename_or_id: int | str, lowercase: bool = False) -> str:
+def build_doc_url(base_url: str, filename_or_id: int | str, case: Literal['lower', 'title'] | None = None) -> str:
     file_stem = coerce_file_stem(filename_or_id)
-    file_stem = file_stem.lower() if lowercase else file_stem
-    return f"{base_url}/{file_stem}"
+    file_stem = file_stem.lower() if case == 'lower' else file_stem
+    file_stem = file_stem.title() if case == 'title' else file_stem
+    return f"{base_url}{file_stem}"
 
 
 def external_doc_link_markup(site: ExternalSite, filename_or_id: int | str, style: str = TEXT_LINK) -> str: