epstein-files 1.0.5__tar.gz → 1.0.6__tar.gz

{epstein_files-1.0.5 → epstein_files-1.0.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: epstein-files
-Version: 1.0.5
+Version: 1.0.6
 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
@@ -70,6 +70,9 @@ epstein_show --raw 030999
 # This also works:
 epstein_show HOUSE_OVERSIGHT_030999
 
+# Count words used by Epstein and Bannon
+epstein_word_count --name 'Jeffrey Epstein' --name 'Steve Bannon'
+
 # Diff two epstein files after all the cleanup (stripping BOMs, matching newline chars, etc):
 epstein_diff 030999 020442
 ```

{epstein_files-1.0.5 → epstein_files-1.0.6}/README.md

@@ -38,6 +38,9 @@ epstein_show --raw 030999
 # This also works:
 epstein_show HOUSE_OVERSIGHT_030999
 
+# Count words used by Epstein and Bannon
+epstein_word_count --name 'Jeffrey Epstein' --name 'Steve Bannon'
+
 # Diff two epstein files after all the cleanup (stripping BOMs, matching newline chars, etc):
 epstein_diff 030999 020442
 ```

{epstein_files-1.0.5 → epstein_files-1.0.6}/epstein_files/__init__.py

@@ -10,11 +10,12 @@ from sys import exit
 
 from dotenv import load_dotenv
 load_dotenv()
-
 from rich.markup import escape
 from rich.padding import Padding
 from rich.panel import Panel
+from rich.text import Text
 
+from epstein_files.count_words import write_word_counts_html
 from epstein_files.epstein_files import EpsteinFiles, document_cls
 from epstein_files.documents.document import INFO_PADDING, Document
 from epstein_files.documents.email import Email
@@ -24,22 +25,25 @@ 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_metadata, print_json_stats, print_text_messages, write_urls
+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.rich import build_highlighter, console, print_header, print_panel, write_html
 from epstein_files.util.timer import Timer
 
+timer = Timer()
+epstein_files = EpsteinFiles.get_files(timer)
+
 
 def generate_html() -> None:
     if args.make_clean:
         make_clean()
+        write_urls()
         exit()
-
-    timer = Timer()
-    epstein_files = EpsteinFiles.get_files(timer)
-
-    if args.json_metadata:
+    elif args.json_metadata:
         print_json_metadata(epstein_files)
         exit()
+    elif args.output_json_files:
+        print_json_files(epstein_files)
+        exit()
 
     print_header(epstein_files)
 
@@ -108,22 +112,22 @@ def epstein_show():
     console.line()
 
     for doc in docs:
-        console.line()
-        console.print(doc)
+        if isinstance(doc, Email):
+            doc.truncation_allowed = False
+
+        console.print('\n', doc, '\n')
 
         if args.raw:
-            console.line()
-            console.print(Panel(f"RAW {doc.filename} RAW", expand=False, style=doc._border_style()))
-            console.print(escape(doc.raw_text()))
+            console.print(Panel(Text("RAW: ").append(doc.summary()), expand=False, style=doc._border_style()))
+            console.print(escape(doc.raw_text()), '\n')
 
             if isinstance(doc, Email):
-                console.line()
-                console.print(Panel(f"{doc.filename}: actual_text() output", expand=False, style=doc._border_style()))
-                console.print(escape(doc._actual_text()))
+                console.print(Panel(Text("actual_text: ").append(doc.summary()), expand=False, style=doc._border_style()))
+                console.print(escape(doc._actual_text()), '\n')
 
 
-def epstein_dump_urls() -> None:
-    write_urls()
+def epstein_word_count() -> None:
+    write_word_counts_html()
 
 
 def _assert_positional_args():

epstein_files-1.0.6/epstein_files/count_words.py

@@ -0,0 +1,72 @@
+# Count word usage in emails and texts
+import re
+
+from epstein_files.epstein_files import EpsteinFiles
+from epstein_files.util.constant.common_words import COMMON_WORDS_LIST
+from epstein_files.util.constant.output_files import WORD_COUNT_HTML_PATH
+from epstein_files.util.env import args, specified_names
+from epstein_files.util.logging import logger
+from epstein_files.util.rich import (console, print_centered, print_color_key, print_page_title, print_panel,
+     print_starred_header, write_html)
+from epstein_files.util.search_result import MatchedLine, SearchResult
+from epstein_files.util.timer import Timer
+from epstein_files.util.word_count import WordCount
+
+HTML_REGEX = re.compile(r"^http|#yiv")
+
+
+def write_word_counts_html() -> None:
+    timer = Timer()
+    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.emails
+        if not (e.is_duplicate or e.is_junk_mail() or (e.config and e.config.is_fwded_article)) \
+            and (len(specified_names) == 0 or e.author in specified_names)
+    ]
+
+    for email in emails:
+        logger.info(f"Counting words in {email}\n  [SUBJECT] {email.subject()}")
+        lines = email.actual_text.split('\n')
+
+        if email.subject() not in email_subjects and f'Re: {email.subject()}' not in email_subjects:
+            email_subjects.add(email.subject())
+            lines.append(email.subject())
+
+        for i, line in enumerate(lines):
+            if HTML_REGEX.search(line):
+                continue
+
+            for word in line.split():
+                word_count.tally_word(word, SearchResult(email, [MatchedLine(line, i)]))
+
+    # Add in iMessage conversation words
+    imessage_logs = epstein_files.imessage_logs_for(specified_names) if specified_names else epstein_files.imessage_logs
+
+    for imessage_log in imessage_logs:
+        logger.info(f"Counting words in {imessage_log}")
+
+        for msg in imessage_log.messages():
+            if len(specified_names) > 0 and msg.author not in specified_names:
+                continue
+            elif HTML_REGEX.search(line):
+                continue
+
+            for word in msg.text.split():
+                word_count.tally_word(word, SearchResult(imessage_log, [msg.text]))
+
+    print_page_title(expand=False)
+    print_starred_header(f"Most Common Words in {len(emails):,} Emails and {len(imessage_logs)} iMessage Logs")
+    print_centered(f"(excluding {len(COMMON_WORDS_LIST)} particularly common words at bottom)", style='dim')
+    console.line()
+    print_color_key()
+    console.line()
+    console.print(word_count)
+    console.line(2)
+    print_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-1.0.5 → epstein_files-1.0.6}/epstein_files/documents/json_file.py

@@ -21,14 +21,11 @@ class JsonFile(OtherFile):
         if self.url_slug.endswith('.txt') or self.url_slug.endswith('.json'):
             self.url_slug = Path(self.url_slug).stem
 
-        self._set_computed_fields(text=self.formatted_json())
+        self._set_computed_fields(text=self.json_str())
 
     def category(self) -> str:
         return JSON
 
-    def formatted_json(self) -> str:
-        return json.dumps(self.json_data(), indent=4)
-
     def info_txt(self) -> Text | None:
         return Text(f"JSON file, possibly iMessage or similar app metadata", style='white dim italic')
 
@@ -38,3 +35,6 @@ class JsonFile(OtherFile):
     def json_data(self) -> object:
         with open(self.file_path, encoding='utf-8-sig') as f:
             return json.load(f)
+
+    def json_str(self) -> str:
+        return json.dumps(self.json_data(), indent=4)

{epstein_files-1.0.5 → epstein_files-1.0.6}/epstein_files/documents/messenger_log.py

@@ -15,6 +15,7 @@ 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
 
 CONFIRMED_MSG = 'Found confirmed counterparty'
 GUESSED_MSG = 'This is probably a conversation with'
@@ -111,7 +112,7 @@ class MessengerLog(Communication):
     @classmethod
     def summary_table(cls, imessage_logs: list['MessengerLog']) -> Table:
         """Build a table summarizing the text messages in 'imessage_logs'."""
-        counts_table = Table(title="Text Message Counts By Author", header_style="bold")
+        counts_table = build_table("Text Message Counts By Author")
         counts_table.add_column(AUTHOR.title(), justify='left', style="steel_blue bold", width=30)
         counts_table.add_column('Files', justify='right', style='white')
         counts_table.add_column("Msgs", justify='right')

{epstein_files-1.0.5 → epstein_files-1.0.6}/epstein_files/documents/other_file.py

@@ -20,7 +20,7 @@ from epstein_files.util.data import escape_single_quotes, remove_timezone, uniqu
 from epstein_files.util.file_helper import FILENAME_LENGTH
 from epstein_files.util.env import args
 from epstein_files.util.highlighted_group import get_style_for_category
-from epstein_files.util.rich import QUESTION_MARK_TXT, highlighter
+from epstein_files.util.rich import QUESTION_MARK_TXT, build_table, highlighter
 from epstein_files.util.logging import logger
 
 MAX_DAYS_SPANNED_TO_BE_VALID = 10
@@ -233,7 +233,7 @@ class OtherFile(Document):
     @staticmethod
     def build_table(docs: list['OtherFile']) -> Table:
         """Build a table of OtherFile documents."""
-        table = Table(header_style='bold', show_lines=True)
+        table = build_table(None, show_lines=True)
         table.add_column('File', justify='center', width=FILENAME_LENGTH)
         table.add_column('Date', justify='center')
         table.add_column('Size', justify='center')

{epstein_files-1.0.5 → epstein_files-1.0.6}/epstein_files/epstein_files.py

@@ -28,9 +28,9 @@ from epstein_files.util.doc_cfg import EmailCfg, Metadata
 from epstein_files.util.env import args, logger
 from epstein_files.util.file_helper import DOCS_DIR, 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, 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.rich import (DEFAULT_NAME_STYLE, NA_TXT, TABLE_BORDER_STYLE, 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
 from epstein_files.util.timer import Timer
 
@@ -212,7 +212,7 @@ class EpsteinFiles:
         return [doc for doc in self.other_files if not isinstance(doc, JsonFile)]
 
     def print_files_summary(self) -> None:
-        table = Table(title='Summary of Document Types')
+        table = build_table('Summary of Document Types')
         add_cols_to_table(table, ['File Type', 'Files', 'Author Known', 'Author Unknown', 'Duplicates'])
 
         def add_row(label: str, docs: list):
@@ -268,12 +268,12 @@ class EpsteinFiles:
 
     def print_email_device_info(self) -> None:
         print_panel(f"Email [italic]Sent from \\[DEVICE][/italic] Signature Breakdown", padding=(4, 0, 0, 0), centered=True)
-        console.print(build_signature_table(self.email_authors_to_device_signatures, (AUTHOR, DEVICE_SIGNATURE)))
-        console.print(build_signature_table(self.email_device_signatures_to_authors, (DEVICE_SIGNATURE, AUTHOR), ', '))
+        console.print(_build_signature_table(self.email_authors_to_device_signatures, (AUTHOR, DEVICE_SIGNATURE)))
+        console.print(_build_signature_table(self.email_device_signatures_to_authors, (DEVICE_SIGNATURE, AUTHOR), ', '))
 
     def print_emailer_counts_table(self) -> None:
         footer = f"Identified authors of {self.attributed_email_count():,} emails out of {len(self.emails):,}."
-        counts_table = Table(title=f"Email Counts", caption=footer, header_style="bold")
+        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'])
 
         emailer_counts = {
@@ -345,21 +345,6 @@ class EpsteinFiles:
                 self.email_device_signatures_to_authors[email.sent_from_device].add(email.author_or_unknown())
 
 
-def build_signature_table(keyed_sets: dict[str, set[str]], cols: tuple[str, str], join_char: str = '\n') -> Padding:
-    title = 'Signatures Used By Authors' if cols[0] == AUTHOR else 'Authors Seen Using Signatures'
-    table = Table(header_style="bold reverse", show_lines=True, title=title)
-
-    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 count_by_month(docs: Sequence[Document]) -> dict[str | None, int]:
     counts: dict[str | None, int] = defaultdict(int)
 
@@ -397,6 +382,21 @@ def is_ok_for_epstein_web(name: str | None) -> bool:
     return True
 
 
+def _build_signature_table(keyed_sets: dict[str, set[str]], cols: tuple[str, str], join_char: str = '\n') -> Padding:
+    title = 'Signatures Used By Authors' if cols[0] == AUTHOR else 'Authors Seen Using 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 _sorted_metadata(docs: Sequence[Document]) -> list[Metadata]:
     docs_sorted_by_id = sorted(docs, key=lambda d: d.file_id)
     return [json_safe(d.metadata()) for d in docs_sorted_by_id]

{epstein_files-1.0.5 → epstein_files-1.0.6}/epstein_files/util/constant/output_files.py

@@ -1,19 +1,36 @@
 from pathlib import Path
 
-URLS_ENV = '.urls.env'
+from epstein_files.util.constant.strings import EMAIL, TEXT_MESSAGE, SiteType
 
 # Files output by the code
 HTML_DIR = Path('docs')
 EPSTEIN_FILES_NOV_2025 = 'epstein_files_nov_2025'
 ALL_EMAILS_PATH = HTML_DIR.joinpath(f'all_emails_{EPSTEIN_FILES_NOV_2025}.html')
+JSON_FILES_JSON_PATH = HTML_DIR.joinpath(f'json_files_from_{EPSTEIN_FILES_NOV_2025}.json')
 JSON_METADATA_PATH = HTML_DIR.joinpath(f'file_metadata_{EPSTEIN_FILES_NOV_2025}.json')
 TEXT_MSGS_HTML_PATH = HTML_DIR.joinpath('index.html')
 WORD_COUNT_HTML_PATH = HTML_DIR.joinpath(f'communication_word_count_{EPSTEIN_FILES_NOV_2025}.html')
 # EPSTEIN_WORD_COUNT_HTML_PATH = HTML_DIR.joinpath('epstein_texts_and_emails_word_count.html')
+URLS_ENV = '.urls.env'
+
+# Deployment URLS
+# NOTE: don't rename these variables without changing deploy.sh!
+GH_PAGES_BASE_URL = 'https://michelcrypt4d4mus.github.io'
+TEXT_MSGS_URL = f"{GH_PAGES_BASE_URL}/epstein_text_messages"
+ALL_EMAILS_URL = f"{TEXT_MSGS_URL}/{ALL_EMAILS_PATH.name}"
+JSON_FILES_URL = f"{TEXT_MSGS_URL}/{JSON_FILES_JSON_PATH.name}"
+JSON_METADATA_URL = f"{TEXT_MSGS_URL}/{JSON_METADATA_PATH.name}"
+WORD_COUNT_URL = f"{TEXT_MSGS_URL}/{WORD_COUNT_HTML_PATH.name}"
+
+SITE_URLS: dict[SiteType, str] = {
+    EMAIL: ALL_EMAILS_URL,
+    TEXT_MESSAGE: TEXT_MSGS_URL,
+}
 
 BUILD_ARTIFACTS = [
     ALL_EMAILS_PATH,
     # EPSTEIN_WORD_COUNT_HTML_PATH,
+    JSON_FILES_JSON_PATH,
     JSON_METADATA_PATH,
     TEXT_MSGS_HTML_PATH,
     WORD_COUNT_HTML_PATH,

{epstein_files-1.0.5 → epstein_files-1.0.6}/epstein_files/util/constant/strings.py

@@ -49,7 +49,6 @@ TEXT_MESSAGE = 'text message'
 SiteType = Literal['email', 'text message']
 
 # Styles
-OTHER_SITE_LINK_STYLE = 'dark_goldenrod'
 TIMESTAMP_STYLE = 'turquoise4'
 TIMESTAMP_DIM = f"turquoise4 dim"
 

{epstein_files-1.0.5 → epstein_files-1.0.6}/epstein_files/util/constant/urls.py

@@ -6,7 +6,6 @@ from inflection import parameterize
 from rich.text import Text
 
 from epstein_files.util.constant.output_files import *
-from epstein_files.util.constant.strings import EMAIL, TEXT_MESSAGE, SiteType
 from epstein_files.util.file_helper import coerce_file_stem
 
 # Style stuff
@@ -15,26 +14,11 @@ TEXT_LINK = 'text_link'
 
 # External site names
 ExternalSite = Literal['epstein.media', 'epsteinify', 'EpsteinWeb']
-
 EPSTEIN_MEDIA = 'epstein.media'
 EPSTEIN_WEB = 'EpsteinWeb'
 EPSTEINIFY = 'epsteinify'
 JMAIL = 'Jmail'
 
-
-# Deployment URLS
-# NOTE: don't rename these variables without changing deploy.sh!
-GH_PAGES_BASE_URL = 'https://michelcrypt4d4mus.github.io'
-TEXT_MSGS_URL = f"{GH_PAGES_BASE_URL}/epstein_text_messages"
-ALL_EMAILS_URL = f'{TEXT_MSGS_URL}/{ALL_EMAILS_PATH.name}'
-JSON_METADATA_URL = f'{TEXT_MSGS_URL}/{JSON_METADATA_PATH.name}'
-WORD_COUNT_URL = f'{TEXT_MSGS_URL}/{WORD_COUNT_HTML_PATH.name}'
-
-SITE_URLS: dict[SiteType, str] = {
-    EMAIL: ALL_EMAILS_URL,
-    TEXT_MESSAGE: TEXT_MSGS_URL,
-}
-
 GH_PROJECT_URL = 'https://github.com/michelcrypt4d4mus/epstein_text_messages'
 GH_MASTER_URL = f"{GH_PROJECT_URL}/blob/master"
 ATTRIBUTIONS_URL = f'{GH_MASTER_URL}/epstein_files/util/constants.py'
@@ -46,13 +30,15 @@ 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'
+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'
+
+# Document source sites
 EPSTEINIFY_URL = 'https://epsteinify.com'
 EPSTEIN_MEDIA_URL = 'https://epstein.media'
 EPSTEIN_WEB_URL = 'https://epsteinweb.org'
 JMAIL_URL = 'https://jmail.world'
-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'
 
 DOC_LINK_BASE_URLS: dict[ExternalSite, str] = {
     EPSTEIN_MEDIA: f"{EPSTEIN_MEDIA_URL}/files",
@@ -61,7 +47,6 @@ DOC_LINK_BASE_URLS: dict[ExternalSite, str] = {
 }
 
 
-# TODO: epsteinify.com seems to be down as of 2025-12-30, switched to epstein.web for links
 epsteinify_api_url = lambda file_id: f"{EPSTEINIFY_URL}/api/documents/HOUSE_OVERSIGHT_{file_id}"
 epsteinify_doc_link_markup = lambda filename_or_id, style = TEXT_LINK: external_doc_link_markup(EPSTEINIFY, filename_or_id, style)
 epsteinify_doc_link_txt = lambda filename_or_id, style = TEXT_LINK: Text.from_markup(external_doc_link_markup(filename_or_id, style))

{epstein_files-1.0.5 → epstein_files-1.0.6}/epstein_files/util/env.py

@@ -6,9 +6,9 @@ from sys import argv
 
 from epstein_files.util.logging import datefinder_logger, env_log_level, logger
 
-COUNT_WORDS_SCRIPT = 'count_words.py'
+COUNT_WORDS_SCRIPT = 'epstein_word_count'
 DEFAULT_WIDTH = 145
-HTML_SCRIPTS = ['epstein_generate', 'generate_html.py', COUNT_WORDS_SCRIPT]
+HTML_SCRIPTS = ['epstein_generate', COUNT_WORDS_SCRIPT]
 
 
 parser = ArgumentParser(description="Parse epstein OCR docs and generate HTML page.")
@@ -19,8 +19,9 @@ output = parser.add_argument_group('OUTPUT')
 output.add_argument('--all-emails', '-ae', action='store_true', help='all the emails instead of just the interesting ones')
 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')
 output.add_argument('--build', '-b', action='store_true', help='write output to HTML file')
-output.add_argument('--make-clean', '-mc', action='store_true', help='delete all build artifact HTML and JSON files')
+output.add_argument('--make-clean', action='store_true', help='delete all HTML build artifact and write latest URLs to .urls.env')
 output.add_argument('--output-emails', '-oe', action='store_true', help='generate other files section')
+output.add_argument('--output-json-files', action='store_true', help='pretty print all the raw JSON data files in the collection')
 output.add_argument('--output-other-files', '-oo', action='store_true', help='generate other files section')
 output.add_argument('--output-texts', '-ot', action='store_true', help='generate other files section')
 output.add_argument('--suppress-output', action='store_true', help='no output to terminal (use with --build)')

{epstein_files-1.0.5 → epstein_files-1.0.6}/epstein_files/util/output.py

@@ -1,12 +1,14 @@
+import json
+
 from rich.padding import Padding
 
 from epstein_files.documents.email import Email
 from epstein_files.documents.messenger_log import MessengerLog
 from epstein_files.epstein_files import EpsteinFiles, count_by_month
-from epstein_files.util.constant.output_files import JSON_METADATA_PATH
-from epstein_files.util.constant import urls
+from epstein_files.util.constant 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.data import dict_sets_to_lists
 from epstein_files.util.env import args, specified_names
 from epstein_files.util.logging import log_file_write, logger
@@ -107,6 +109,20 @@ def print_emails(epstein_files: EpsteinFiles) -> int:
     return len(already_printed_emails)
 
 
+def print_json_files(epstein_files: EpsteinFiles):
+    if args.build:
+        json_data = {json_file.url_slug: json_file.json_data() for json_file in epstein_files.json_files}
+
+        with open(JSON_FILES_JSON_PATH, 'w') as f:
+            f.write(json.dumps(json_data, sort_keys=True))
+            log_file_write(JSON_FILES_JSON_PATH)
+    else:
+        for json_file in epstein_files.json_files:
+            console.line(2)
+            console.print(json_file.description_panel())
+            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()
 
@@ -146,10 +162,10 @@ def print_text_messages(epstein_files: EpsteinFiles) -> None:
 
 def write_urls() -> None:
     """Write _URL style constant variables to a file bash scripts can load as env vars."""
-    url_vars = {
-        k: v for k, v in vars(urls).items()
-        if isinstance(v, str) and k.split('_')[-1] in ['URL'] and 'github.io' in v and 'BASE' not in k
-    }
+    url_vars = {k: v for k, v in vars(output_files).items() if k.endswith('URL') and not k.startswith('GH')}
+
+    if not args.suppress_output:
+        console.line()
 
     with open(URLS_ENV, 'w') as f:
         for var_name, url in url_vars.items():
@@ -160,7 +176,9 @@ def write_urls() -> None:
 
             f.write(f"{key_value}\n")
 
-    console.line()
+    if not args.suppress_output:
+        console.line()
+
     logger.warning(f"Wrote {len(url_vars)} URL variables to '{URLS_ENV}'\n")
 
 

{epstein_files-1.0.5 → epstein_files-1.0.6}/epstein_files/util/rich.py

@@ -14,7 +14,8 @@ from rich.theme import Theme
 
 from epstein_files.util.constant.html import CONSOLE_HTML_FORMAT, HTML_TERMINAL_THEME, PAGE_TITLE
 from epstein_files.util.constant.names import UNKNOWN
-from epstein_files.util.constant.strings import DEFAULT, EMAIL, NA, OTHER_SITE_LINK_STYLE, QUESTION_MARKS, SiteType
+from epstein_files.util.constant.output_files import SITE_URLS
+from epstein_files.util.constant.strings import DEFAULT, EMAIL, NA, QUESTION_MARKS, TEXT_MESSAGE, SiteType
 from epstein_files.util.constant.urls import *
 from epstein_files.util.constants import FALLBACK_TIMESTAMP, HEADER_ABBREVIATIONS
 from epstein_files.util.data import json_safe
@@ -31,11 +32,22 @@ GREY_NUMBERS = [58, 39, 39, 35, 30, 27, 23, 23, 19, 19, 15, 15, 15]
 DEFAULT_NAME_STYLE = 'gray46'
 KEY_STYLE='honeydew2 bold'
 SECTION_HEADER_STYLE = 'bold white on blue3'
-SOCIAL_MEDIA_LINK_STYLE = 'cyan3 bold'
+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"
 TITLE_STYLE = 'black on bright_white bold'
 
+AUX_SITE_LINK_STYLE = 'dark_orange3'
+OTHER_SITE_LINK_STYLE = 'dark_goldenrod'
+
+DEFAULT_TABLE_KWARGS = {
+    'border_style': TABLE_BORDER_STYLE,
+    'header_style': "bold",
+    'title_style': TABLE_TITLE_STYLE,
+}
+
 HIGHLIGHTED_GROUP_COLOR_KEYS = [
     Text(highlight_group.label.replace('_', ' '), style=highlight_group.style)
     for highlight_group in sorted(HIGHLIGHTED_NAMES, key=lambda hg: hg.label)
@@ -79,7 +91,11 @@ def build_highlighter(pattern: str) -> EpsteinHighlighter:
     return TempHighlighter()
 
 
-def join_texts(txts: list[Text], join: str = ' ', encloser: str = '') -> Text:
+def build_table(title: str | None, **kwargs) -> Table:
+    return Table(title=title, **{**DEFAULT_TABLE_KWARGS, **kwargs})
+
+
+def join_texts(txts: list[Text], join: str = ' ', encloser: str = '', encloser_style: str = 'wheat4') -> Text:
     """Join rich.Text objs into one."""
     if encloser:
         if len(encloser) != 2:
@@ -91,8 +107,9 @@ def join_texts(txts: list[Text], join: str = ' ', encloser: str = '') -> Text:
 
     txt = Text('')
 
-    for i, link in enumerate(txts):
-        txt.append(join if i >= 1 else '').append(enclose_start).append(link).append(enclose_end)
+    for i, _txt in enumerate(txts):
+        txt.append(join if i >= 1 else '').append(enclose_start, style=encloser_style)
+        txt.append(_txt).append(enclose_end, style=encloser_style)
 
     return txt
 
@@ -132,7 +149,7 @@ def print_centered_link(url: str, link_text: str, style: str | None = None) -> N
 
 
 def print_color_key() -> None:
-    color_table = Table(title=f'Rough Guide to Highlighted Colors', show_header=False)
+    color_table = build_table('Rough Guide to Highlighted Colors', show_header=False)
     num_colors = len(HIGHLIGHTED_GROUP_COLOR_KEYS)
     row_number = 0
 
@@ -164,7 +181,7 @@ def print_header(epstein_files: 'EpsteinFiles') -> None:
     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')
     print_centered(f"(thanks to {link_markup('https://x.com/ImDrinknWyn', '@ImDrinknWyn', 'dodger_blue3')} + others for help attributing redacted emails)")
-    print_centered_link(ATTRIBUTIONS_URL, "(some explanations of author attributions)", style='magenta')
+    print_centered_link(JSON_METADATA_URL, "(explanations of author attributions)", style='magenta')
 
 
 def print_json(label: str, obj: object, skip_falsey: bool = False) -> None:
@@ -233,17 +250,18 @@ def print_other_site_link(is_header: bool = True) -> None:
     print_centered(parenthesize(Text.from_markup(markup_msg)), style='bold')
 
     if is_header:
-        metadata_link = link_text_obj(JSON_METADATA_URL, 'metadata with author attribution explanations', OTHER_SITE_LINK_STYLE)
-        print_centered(parenthesize(metadata_link))
-        word_count_link = link_text_obj(WORD_COUNT_URL, 'most frequently used words', OTHER_SITE_LINK_STYLE)
+        word_count_link = link_text_obj(WORD_COUNT_URL, 'most frequently used words in the emails and texts', AUX_SITE_LINK_STYLE)
         print_centered(parenthesize(word_count_link))
-        print_centered(parenthesize(link_text_obj(GH_PROJECT_URL, '@github', 'dark_orange3 bold')))
+        metadata_link = link_text_obj(JSON_METADATA_URL, 'author attribution explanations', AUX_SITE_LINK_STYLE)
+        print_centered(parenthesize(metadata_link))
+        json_link = link_text_obj(WORD_COUNT_URL, "epstein's json files", AUX_SITE_LINK_STYLE)
+        print_centered(parenthesize(json_link))
 
 
 def print_page_title(expand: bool = True, width: int | None = None) -> None:
     title_panel = Panel(Text(PAGE_TITLE, justify='center'), expand=expand, style=TITLE_STYLE, width=width)
     console.print(Align.center(vertically_pad(title_panel)))
-    print_social_media_links()
+    _print_social_media_links()
     console.line(2)
 
 
@@ -265,19 +283,6 @@ def print_section_header(msg: str, style: str = SECTION_HEADER_STYLE, is_centere
     console.print(Padding(panel, (3, 0, 1, 0)))
 
 
-def print_social_media_links() -> None:
-    print_centered_link(SUBSTACK_URL, "I Made Epstein's Text Messages Great Again (And You Should Read Them)", style=f'{SUBSTACK_POST_LINK_STYLE} bold')
-    print_centered_link(SUBSTACK_URL, SUBSTACK_URL.removeprefix('https://'), style=f'{SUBSTACK_POST_LINK_STYLE} dim')
-
-    social_links = [
-        link_text_obj('https://x.com/Cryptadamist/status/1990866804630036988', '@cryptadamist', style=SOCIAL_MEDIA_LINK_STYLE),
-        link_text_obj('https://cryptadamus.substack.com/', 'substack', style=SOCIAL_MEDIA_LINK_STYLE),
-        link_text_obj('https://universeodon.com/@cryptadamist/115572634993386057', 'mastodon', style=SOCIAL_MEDIA_LINK_STYLE),
-    ]
-
-    print_centered(join_texts(social_links, join='     ', encloser='[]'))
-
-
 def print_starred_header(msg: str, num_stars: int = 7, num_spaces: int = 2, style: str = TITLE_STYLE) -> None:
     stars = '*' * num_stars
     spaces = ' ' * num_spaces
@@ -317,7 +322,7 @@ def write_html(output_path: Path) -> None:
 
 
 def _print_abbreviations_table() -> None:
-    table = Table(title="Abbreviations Used Frequently In These Conversations", header_style="bold", show_header=False)
+    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")
 
@@ -329,7 +334,7 @@ def _print_abbreviations_table() -> None:
 
 def _print_external_links() -> None:
     console.line()
-    print_starred_header('External Links', num_stars=0, num_spaces=20, style=f"italic")
+    print_centered(Text('External Links', style=TABLE_TITLE_STYLE))
     presser_link = link_text_obj(OVERSIGHT_REPUBLICANS_PRESSER_URL, 'Official Oversight Committee Press Release')
     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]))
@@ -341,5 +346,24 @@ def _print_external_links() -> None:
     print_centered(link_markup(EPSTEIN_MEDIA_URL) + " (raw document images)")
 
 
+def _print_social_media_links() -> None:
+    print_centered_link(
+        SUBSTACK_URL,
+        "I Made Epstein's Text Messages Great Again (And You Should Read Them)",
+        style=f'{SUBSTACK_POST_LINK_STYLE} bold'
+    )
+
+    print_centered_link(SUBSTACK_URL, SUBSTACK_URL.removeprefix('https://'), style=f'{SUBSTACK_POST_LINK_STYLE} dim')
+
+    social_links = [
+        link_text_obj('https://universeodon.com/@cryptadamist/115572634993386057', '@mastodon', style=SOCIAL_MEDIA_LINK_STYLE),
+        link_text_obj(SUBSTACK_URL, '@substack', style=SOCIAL_MEDIA_LINK_STYLE),
+        link_text_obj('https://x.com/Cryptadamist/status/1990866804630036988', '@twitter', style=SOCIAL_MEDIA_LINK_STYLE),
+        link_text_obj('https://github.com/michelcrypt4d4mus/epstein_text_messages', '@github', style=SOCIAL_MEDIA_LINK_STYLE)
+    ]
+
+    print_centered(join_texts(social_links, join='  /  '))#, encloser='()'))#, encloser='‹›'))
+
+
 # if args.deep_debug:
 #     print_json('THEME_STYLES', THEME_STYLES)

{epstein_files-1.0.5 → epstein_files-1.0.6}/epstein_files/util/word_count.py

@@ -20,6 +20,14 @@ from epstein_files.util.search_result import SearchResult
 FIRST_AND_LAST_NAMES = flatten([n.split() for n in ALL_NAMES])
 FIRST_AND_LAST_NAMES = [n.lower() for n in FIRST_AND_LAST_NAMES] + OTHER_NAMES
 
+HTML_REGEX = re.compile(r"com/|cae-v2w=|content-(transfe|type)|font(/|-(family|size))|http|\.html?\??|margin-bottom|padding-left|quoted-printable|region=|text-decoration|ttps|www|\.(gif|jpe?g|png);?$")
+HYPHENATED_WORD_REGEX = re.compile(r"[a-z]+-[a-z]+", re.IGNORECASE)
+OK_SYMBOL_WORDS = ['mar-a-lago', 'p/e', 's&p', ':)', ':).', ';)', ':-)', ';-)']
+ONLY_SYMBOLS_REGEX = re.compile(r"^[^a-zA-Z0-9]+$")
+SYMBOL_WORD_REGEX = re.compile(r"^[-—–@%/?.,&=]+$")
+SPLIT_WORDS_BY = ['@', '/']
+FLAGGED_WORDS = []  # For debugging, log extra info when one of these is encountered
+
 NON_SINGULARIZABLE = UNSINGULARIZABLE_WORDS + [n for n in FIRST_AND_LAST_NAMES if n.endswith('s')]
 SKIP_WORDS_REGEX = re.compile(r"^(asmallworld@|enwiki|http|imagepng|nymagcomnymetro|addresswww|mailto|www|/font|colordu|classdms|targetdblank|nymagcom|palmbeachdailynews)|jee[vy]acation|fontfamily|(gif|html?|jpe?g|utm)$")
 BAD_CHARS_REGEX = re.compile(r"[-–=+()$€£©°«—^&%!#_`,.;:'‘’\"„“”?\d\\]")
@@ -100,21 +108,13 @@ SINGULARIZATIONS = {
     'twittercom': 'twitter',
 }
 
-HTML_REGEX = re.compile(r"com/|cae-v2w=|content-(transfe|type)|font(/|-(family|size))|http|\.html?\??|margin-bottom|padding-left|quoted-printable|region=|text-decoration|ttps|www|\.(gif|jpe?g|png);?$")
-HYPHENATED_WORD_REGEX = re.compile(r"[a-z]+-[a-z]+", re.IGNORECASE)
-OK_SYMBOL_WORDS = ['mar-a-lago', 'p/e', 's&p', ':)', ':).', ';)', ':-)', ';-)']
-SYMBOL_WORD_REGEX = re.compile(r"^[-—–@%/?.,&=]+$")
-ONLY_SYMBOLS_REGEX = re.compile(r"^[^a-zA-Z0-9]+$")
-SPLIT_WORDS_BY = ['@', '/']
-FLAGGED_WORDS = []  # For debugging, log extra info when one of these is encountered
-
 
 @dataclass
 class WordCount:
     count: dict[str, int] = field(default_factory=lambda: defaultdict(int))
     singularized: dict[str, int] = field(default_factory=lambda: defaultdict(int))
 
-    def count_word(self, word: str, document_line: SearchResult) -> None:
+    def tally_word(self, word: str, document_line: SearchResult) -> None:
         word = EmailHeader.cleanup_str(word).lower().strip()
         raw_word = word
 
@@ -148,7 +148,7 @@ class WordCount:
                 continue
 
             for w in word.split(symbol):
-                self.count_word(w, document_line)
+                self.tally_word(w, document_line)
 
             logger.info(f"  Split word with '{symbol}' in it '{word}'...")
             return

{epstein_files-1.0.5 → epstein_files-1.0.6}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "epstein-files"
-version = "1.0.5"
+version = "1.0.6"
 description = "Tools for working with the Jeffrey Epstein documents released in November 2025."
 authors = ["Michel de Cryptadamus"]
 readme = "README.md"
@@ -44,10 +44,10 @@ pytest = "^9.0.1"
 
 [tool.poetry.scripts]
 epstein_diff = 'epstein_files:epstein_diff'
-epstein_dump_urls = 'epstein_files:epstein_dump_urls'
 epstein_generate = 'epstein_files:generate_html'
 epstein_search = 'epstein_files:epstein_search'
 epstein_show = 'epstein_files:epstein_show'
+epstein_word_count = 'epstein_files:epstein_word_count'
 
 
 [tool.poetry.urls]