epstein-files 1.2.0__py3-none-any.whl → 1.2.1__py3-none-any.whl

epstein_files/person.py

@@ -1,5 +1,6 @@
 from dataclasses import dataclass, field
 from datetime import datetime, date
+from typing import Sequence
 
 from rich.console import Group, RenderableType
 from rich.padding import Padding
@@ -18,13 +19,14 @@ from epstein_files.util.data import days_between, flatten, without_falsey
 from epstein_files.util.env import args
 from epstein_files.util.highlighted_group import (QUESTION_MARKS_TXT, HighlightedNames,
      get_highlight_group_for_name, get_style_for_name, styled_category, styled_name)
-from epstein_files.util.rich import GREY_NUMBERS, LAST_TIMESTAMP_STYLE, TABLE_TITLE_STYLE, build_table, console, join_texts, print_centered
+from epstein_files.util.rich import GREY_NUMBERS, TABLE_TITLE_STYLE, build_table, console, join_texts, print_centered
 
 ALT_INFO_STYLE = 'medium_purple4'
 CC = 'cc:'
 MIN_AUTHOR_PANEL_WIDTH = 80
 EMAILER_INFO_TITLE = 'Email Conversations Will Appear'
-UNINTERESTING_CC_INFO = "CC: or BCC: recipient only"
+UNINTERESTING_CC_INFO = "cc: or bcc: recipient only"
+UNINTERESTING_CC_INFO_NO_CONTACT = f"{UNINTERESTING_CC_INFO}, no direct contact with Epstein"
 
 INVALID_FOR_EPSTEIN_WEB = JUNK_EMAILERS + MAILING_LISTS + [
     'ACT for America',
@@ -100,6 +102,10 @@ class Person:
         links = [self.external_link_txt(site) for site in PERSON_LINK_BUILDERS]
         return Text('', justify='center', style='dim').append(join_texts(links, join=' / '))  #, encloser='()'))#, encloser='‹›'))
 
+    def has_any_epstein_emails(self) -> bool:
+        contacts = [e.author for e in self.emails] + flatten([e.recipients for e in self.emails])
+        return JEFFREY_EPSTEIN in contacts
+
     def highlight_group(self) -> HighlightedNames | None:
         return get_highlight_group_for_name(self.name)
 
@@ -132,7 +138,10 @@ class Person:
         if highlight_group and isinstance(highlight_group, HighlightedNames) and self.name:
             return highlight_group.info_for(self.name)
         elif self.is_uninteresting_cc:
-            return UNINTERESTING_CC_INFO
+            if self.has_any_epstein_emails():
+                return UNINTERESTING_CC_INFO
+            else:
+                return UNINTERESTING_CC_INFO_NO_CONTACT
 
     def info_with_category(self) -> str:
         return ', '.join(without_falsey([self.category(), self.info_str()]))
@@ -144,13 +153,18 @@ class Person:
             return Text('(emails whose author or recipient could not be determined)', style=ALT_INFO_STYLE)
         elif self.category() == JUNK:
             return Text(f"({JUNK} mail)", style='tan dim')
+        elif self.is_uninteresting_cc and (self.info_str() or '').startswith(UNINTERESTING_CC_INFO):
+            if self.info_str() == UNINTERESTING_CC_INFO:
+                return Text(f"({self.info_str()})", style='wheat4 dim')
+            else:
+                return Text(f"({self.info_str()})", style='plum4 dim')
         elif self.is_a_mystery():
-            return Text(QUESTION_MARKS, style='magenta dim')
-        elif self.is_uninteresting_cc and self.info_str() == UNINTERESTING_CC_INFO:
-            return Text(f"({self.info_str()})", style='wheat4 dim')
+            return Text(QUESTION_MARKS, style='honeydew2 bold')
         elif self.info_str() is None:
             if self.name in MAILING_LISTS:
-                return Text('(mailing list)', style=f"{self.style()} dim")
+                return Text('(mailing list)', style=f"pale_turquoise4 dim")
+            elif self.category():
+                return Text(QUESTION_MARKS, style=self.style())
             else:
                 return None
         else:
@@ -214,8 +228,8 @@ class Person:
         return self._printable_emails()
 
     def print_emails_table(self) -> None:
-        emails = [email for email in self._printable_emails() if not email.is_duplicate()]  # Remove dupes
-        print_centered(Padding(Email.build_emails_table(emails, self.name), (0, 5, 0, 5)))
+        table = Email.build_emails_table(self._unique_printable_emails(), self.name)
+        print_centered(Padding(table, (0, 5, 0, 5)))
 
         if self.is_linkable():
             print_centered(self.external_links_line())
@@ -223,7 +237,7 @@ class Person:
         console.line()
 
     def sort_key(self) -> list[int | str]:
-        counts = [len(self.unique_emails())]
+        counts = [len(self.unique_emails()), int(self.has_any_epstein_emails())]
         counts = [-1 * count for count in counts]
 
         if args.sort_alphabetical:
@@ -234,14 +248,14 @@ class Person:
     def style(self) -> str:
         return get_style_for_name(self.name)
 
-    def unique_emails(self) -> list[Email]:
-        return [email for email in self.emails if not email.is_duplicate()]
+    def unique_emails(self) -> Sequence[Email]:
+        return Document.without_dupes(self.emails)
 
     def unique_emails_by(self) -> list[Email]:
-        return [email for email in self.emails_by() if not email.is_duplicate()]
+        return Document.without_dupes(self.emails_by())
 
     def unique_emails_to(self) -> list[Email]:
-        return [email for email in self.emails_to() if not email.is_duplicate()]
+        return Document.without_dupes(self.emails_to())
 
     def _printable_emails(self):
         """For Epstein we only want to print emails he sent to himself."""
@@ -250,24 +264,27 @@ class Person:
         else:
             return self.emails
 
+    def _unique_printable_emails(self):
+        return Document.without_dupes(self._printable_emails())
+
     def __str__(self):
         return f"{self.name_str()}"
 
     @staticmethod
-    def emailer_info_table(people: list['Person'], highlighted: list['Person'] | None = None) -> Table:
+    def emailer_info_table(people: list['Person'], highlighted: list['Person'] | None = None, show_epstein_total: bool = False) -> Table:
         """Table of info about emailers."""
         highlighted = highlighted or people
         highlighted_names = [p.name for p in highlighted]
-        is_selection = len(people) != len(highlighted) or args.emailers_info_png
+        is_selection = len(people) != len(highlighted) or args.emailers_info
 
         if is_selection:
-            title = Text(f"{EMAILER_INFO_TITLE} in This Order for the Highlighted Names (see ", style=TABLE_TITLE_STYLE)
-            title.append(THE_OTHER_PAGE_TXT).append(" for the rest)")
+            title = Text(f"{EMAILER_INFO_TITLE} in This Order for the Highlighted Names (", style=TABLE_TITLE_STYLE)
+            title.append(THE_OTHER_PAGE_TXT).append(" has the rest)")
         else:
             title = f"{EMAILER_INFO_TITLE} in Chronological Order Based on Timestamp of First Email"
 
         table = build_table(title)
-        table.add_column('Start')
+        table.add_column('First')
         table.add_column('Name', max_width=24, no_wrap=True)
         table.add_column('Category', justify='left', style='dim italic')
         table.add_column('Num', justify='right', style='white')
@@ -296,55 +313,12 @@ class Person:
                 Text(str(earliest_email_date), style=f"grey{GREY_NUMBERS[0 if is_selection else grey_idx]}"),
                 person.name_txt(),  # TODO: make link?
                 person.category_txt(),
-                f"{len(person._printable_emails())}",
-                f"{len(person.unique_emails_by())}",
-                f"{len(person.unique_emails_to())}",
+                f"{len(person.unique_emails() if show_epstein_total else person._unique_printable_emails())}",
+                Text(f"{len(person.unique_emails_by())}", style='dim' if len(person.unique_emails_by()) == 0 else ''),
+                Text(f"{len(person.unique_emails_to())}", style='dim' if len(person.unique_emails_to()) == 0 else ''),
                 f"{person.email_conversation_length_in_days()}",
                 person.info_txt() or '',
                 style='' if person.name in highlighted_names else 'dim',
             )
 
         return table
-
-    @staticmethod
-    def emailer_stats_table(people: list['Person']) -> Table:
-        email_authors = [p for p in people if p.emails_by() and p.name]
-        all_emails = Document.uniquify(flatten([p.unique_emails() for p in people]))
-        attributed_emails = [email for email in all_emails if email.author]
-        footer = f"(identified {len(email_authors)} authors of {len(attributed_emails):,}"
-        footer = f"{footer} out of {len(attributed_emails):,} emails)"
-
-        counts_table = build_table(
-            f"All {len(email_authors)} People Who Sent or Received an Email in the Files",
-            caption=footer,
-            cols=[
-                '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',
-            ]
-        )
-
-        for person in sorted(people, key=lambda person: person.sort_key()):
-            counts_table.add_row(
-                person.name_link(),
-                f"{len(person.unique_emails()):,}",
-                f"{len(person.unique_emails_by()):,}",
-                f"{len(person.unique_emails_to()):,}",
-                str(person.earliest_email_date()),
-                str(person.last_email_date()),
-                f"{person.email_conversation_length_in_days()}",
-                person.external_link_txt(JMAIL),
-                person.external_link_txt(EPSTEIN_MEDIA) if person.is_linkable() else '',
-                person.external_link_txt(EPSTEIN_WEB) if person.is_linkable() else '',
-                person.external_link_txt(TWITTER),
-            )
-
-        return counts_table

epstein_files/util/constant/names.py

@@ -214,11 +214,11 @@ UBS = 'UBS'
 
 # First and last names that should be made part of a highlighting regex for emailers
 NAMES_TO_NOT_HIGHLIGHT = """
-    al alain alan alfredo allen alex alexander amanda andres andrew
-    bard barrett barry bill black bob boris brad bruce
-    carolyn chris christina
+    al alain alan alfredo allen alex alexander amanda andres andrew anthony
+    bard barrett barry bennet bill black bob boris brad bruce
+    caroline carolyn chris christina cohen
     dan daniel danny darren dave david donald
-    ed edward edwards enterprise enterprises entourage epstein eric erika etienne
+    ed edward edwards enforcement enterprise enterprises entourage epstein eric erika etienne
     faith forget fred friendly frost fuller
     gerald george gold gordon
     haddad harry hay heather henry hill hoffman
@@ -226,8 +226,8 @@ NAMES_TO_NOT_HIGHLIGHT = """
     jack james jay jean jeff jeffrey jennifer jeremy jessica joel john jon jonathan joseph jr
     kahn karl kate katherine kelly ken kevin krassner
     larry laurie lawrence leon lesley linda link lisa
-    mann marc marie mark martin melanie michael mike miller mitchell miles morris moskowitz
-    nancy neal new nicole
+    mann marc marie mark martin matthew melanie michael mike miller mitchell miles morris moskowitz
+    nancy neal new nicole norman
     owen
     paul paula pen peter philip prince
     randall rangel reid richard robert rodriguez roger rosenberg ross roth roy rubin
@@ -296,3 +296,10 @@ def extract_last_name(name: str) -> str:
         return ' '.join(first_last_names[-2:])
     else:
         return first_last_names[-1]
+
+
+def reversed_name(name: str) -> str:
+    if ' ' not in name:
+        return name
+
+    return f"{extract_last_name(name)}, {extract_first_name(name)}"

epstein_files/util/constant/strings.py

@@ -9,7 +9,6 @@ ARTICLE = 'article'
 BOOK = 'book'
 BUSINESS = 'business'
 CONFERENCE = 'conference'
-ENTERTAINER = 'entertainer'
 FINANCE = 'finance'
 FRIEND = 'friend'
 FLIGHT_LOG = 'flight log'

epstein_files/util/constant/urls.py

@@ -33,6 +33,7 @@ extracted_file_url = lambda f: f"{EXTRACTS_BASE_URL}/{f}"
 # External URLs
 COFFEEZILLA_ARCHIVE_URL = 'https://journaliststudio.google.com/pinpoint/search?collection=061ce61c9e70bdfd'
 COURIER_NEWSROOM_ARCHIVE_URL = 'https://journaliststudio.google.com/pinpoint/search?collection=092314e384a58618'
+EPSTEIN_DOCS_URL = 'https://epstein-docs.github.io'
 OVERSIGHT_REPUBLICANS_PRESSER_URL = 'https://oversight.house.gov/release/oversight-committee-releases-additional-epstein-estate-documents/'
 RAW_OVERSIGHT_DOCS_GOOGLE_DRIVE_URL = 'https://drive.google.com/drive/folders/1hTNH5woIRio578onLGElkTWofUSWRoH_'
 SUBSTACK_URL = 'https://cryptadamus.substack.com/p/i-made-epsteins-text-messages-great'

epstein_files/util/constants.py

@@ -661,6 +661,7 @@ EMAILS_CONFIG = [
     EmailCfg(id='032023', is_fwded_article=True, duplicate_ids=['032012']),  # American-Israeli Cooperative Enterprise Newsletter
     EmailCfg(id='021758', is_fwded_article=True, duplicate_ids=['030616']),  # Radar Online article about Epstein's early prison release
     EmailCfg(id='033297', is_fwded_article=True, duplicate_ids=['033586']),  # Sultan Sulayem fwding article about Trump and Russia
+    EmailCfg(id='030983', is_fwded_article=True),  # Power Line blog Alex Acosta and Jeffrey Epstein Plea Deal Analysis
     EmailCfg(id='031774', is_fwded_article=True),  # Krassner fwd of Palmer Report article
     EmailCfg(id='033345', is_fwded_article=True),  # Krassner fwd of Palmer Report article
     EmailCfg(id='029903', is_fwded_article=True),  # Krassner fwd of Ann Coulter article about Epstein
@@ -874,7 +875,7 @@ TWEET = 'tweet'
 # Legal cases
 BRUNEL_V_EPSTEIN = f"{JEAN_LUC_BRUNEL} v. {JEFFREY_EPSTEIN} and Tyler McDonald d/b/a YI.org"
 EDWARDS_V_DERSHOWITZ = f"{BRAD_EDWARDS} & {PAUL_G_CASSELL} v. {ALAN_DERSHOWITZ}"
-EPSTEIN_V_ROTHSTEIN_EDWARDS = f"Epstein v. Scott Rothstein, {BRAD_EDWARDS}, and L.M."
+EPSTEIN_V_ROTHSTEIN_EDWARDS = f"Epstein v. Scott Rothstein, {BRAD_EDWARDS}, & L.M."
 GIUFFRE_V_DERSHOWITZ = f"{VIRGINIA_GIUFFRE} v. {ALAN_DERSHOWITZ}"
 GIUFFRE_V_EPSTEIN = f"{VIRGINIA_GIUFFRE} v. {JEFFREY_EPSTEIN}"
 GIUFFRE_V_MAXWELL = f"{VIRGINIA_GIUFFRE} v. {GHISLAINE_MAXWELL}"
@@ -1723,6 +1724,7 @@ UNINTERESTING_EMAILERS = FLIGHT_IN_2012_PEOPLE + IRAN_DEAL_RECIPIENTS + [
     'Oliver Goodenough',                     # Robert Trivers CC
     'Peter Aldhous',                         # Lawrence Krauss CC
     'Players2',                              # Hoffenberg CC
+    'Police Code Enforcement',               # Kirk Blouin / John Page CC
     'Sam Harris',                            # Lawrence Krauss CC
     SAMUEL_LEFF,                             # Random CC
     'Sean T Lehane',                         # Random CC

epstein_files/util/data.py

@@ -29,7 +29,7 @@ escape_single_quotes = lambda text: text.replace("'", r"\'")
 iso_timestamp = lambda dt: dt.isoformat().replace('T', ' ')
 days_between = lambda dt1, dt2: (dt2 - dt1).days + 1
 days_between_str = lambda dt1, dt2: f"{days_between(dt1, dt2)} day" + ('s' if days_between(dt1, dt2) > 1 else '')
-remove_zero_time_from_timestamp_str = lambda dt: dt.isoformat().removesuffix('T00:00:00')
+remove_zero_time = lambda dt: dt.isoformat().removesuffix('T00:00:00')
 uniquify = lambda _list: list(set(_list))
 without_falsey = lambda _list: [e for e in _list if e]
 

epstein_files/util/doc_cfg.py

@@ -8,7 +8,7 @@ from dateutil.parser import parse
 
 from epstein_files.util.constant.names import *
 from epstein_files.util.constant.strings import *
-from epstein_files.util.data import remove_zero_time_from_timestamp_str, without_falsey
+from epstein_files.util.data import remove_zero_time, without_falsey
 
 DuplicateType = Literal['earlier', 'quoted', 'redacted', 'same']
 Metadata = dict[str, bool | datetime | int | str | list[str | None] |dict[str, bool | str]]
@@ -81,6 +81,7 @@ class DocCfg:
     dupe_type: DuplicateType | None = None
     duplicate_ids: list[str] = field(default_factory=list)
     duplicate_of_id: str | None = None
+    is_attribution_uncertain: bool = False
     is_interesting: bool | None = None
     is_synthetic: bool = False
     timestamp: datetime | None = None
@@ -162,7 +163,7 @@ class DocCfg:
             elif _field.name == 'timestamp' and self.date is not None:
                 continue  # Don't print both timestamp and date
             elif isinstance(value, datetime):
-                value_str = remove_zero_time_from_timestamp_str(value)
+                value_str = remove_zero_time(value)
                 add_prop(_field, f"parse('{value_str}')" if CONSTANTIZE_NAMES else f"'{value}'")
             elif isinstance(value, str):
                 if "'" in value:
@@ -206,7 +207,6 @@ class CommunicationCfg(DocCfg):
         is_attribution_uncertain (bool): True if we have a good idea of who the author is but are not 100% certain
     """
     attribution_reason: str | None = None
-    is_attribution_uncertain: bool = False
 
     def __repr__(self) -> str:
         return super().__repr__()

epstein_files/util/env.py

@@ -38,7 +38,7 @@ output.add_argument('--all-emails', '-ae', action='store_true', help='all the em
 output.add_argument('--all-other-files', '-ao', action='store_true', help='all the non-email, non-text msg files instead of just the interesting ones')
 parser.add_argument('--build', '-b', nargs="?", default=None, const=DEFAULT_FILE, help='write output to HTML file')
 output.add_argument('--email-timeline', action='store_true', help='print a table of all emails in chronological order')
-output.add_argument('--emailers-info-png', action='store_true', help='write a .png of the emeailers info table')
+output.add_argument('--emailers-info', action='store_true', help='write a .png of the eeailers info table')
 output.add_argument('--json-files', action='store_true', help='pretty print all the raw JSON data files in the collection and exit')
 output.add_argument('--json-metadata', action='store_true', help='dump JSON metadata for all files and exit')
 output.add_argument('--output-emails', '-oe', action='store_true', help='generate emails section')
@@ -67,9 +67,9 @@ debug.add_argument('--suppress-logs', '-sl', action='store_true', help='set debu
 args = parser.parse_args()
 is_html_script = parser.prog in HTML_SCRIPTS
 
-args.build = args.build or args.emailers_info_png
+args.build = args.build
 args.debug = args.deep_debug or args.debug or is_env_var_set('DEBUG')
-args.names = [None if n == 'None' else n for n in (args.names or [])]
+args.names = [None if n == 'None' else n.strip() for n in (args.names or [])]
 args.output_emails = args.output_emails or args.all_emails
 args.output_other = args.output_other or args.all_other_files or args.uninteresting
 args.overwrite_pickle = args.overwrite_pickle or (is_env_var_set('OVERWRITE_PICKLE') and not is_env_var_set('PICKLED'))
@@ -83,7 +83,7 @@ if is_html_script:
         if any([is_output_arg(arg) and val for arg, val in vars(args).items()]):
             if args.email_timeline:
                 exit_with_error(f"--email-timeline option is mutually exlusive with other output options")
-        elif not args.email_timeline:
+        elif not args.email_timeline and not args.emailers_info:
             logger.warning(f"No output section chosen; outputting default selection of texts, selected emails, and other files...")
             args.output_texts = args.output_emails = args.output_other = True