epstein-files 1.1.2__py3-none-any.whl → 1.1.5__py3-none-any.whl

epstein_files/util/constants.py

@@ -24,7 +24,7 @@ HEADER_ABBREVIATIONS = {
     'Jared': "Jared Kushner",
     'Jagland': 'Thorbjørn Jagland (former Norwegian prime minister)',
     'JEGE': "Epstein's airplane holding company",
-    'Jeffrey Wernick': 'right wing crypto bro, former COO of Parler',
+    JEFFREY_WERNICK: 'right wing crypto bro, former COO of Parler',
     'Joi': f"Joi Ito ({MIT_MEDIA_LAB}, MIT Digital Currency Initiative)",
     "Hoffenberg": f"{STEVEN_HOFFENBERG} (Epstein's ponzi scheme partner)",
     'KSA': "Kingdom of Saudi Arabia",
@@ -89,11 +89,11 @@ EMAILER_ID_REGEXES: dict[str, re.Pattern] = {
     JESSICA_CADWELL: re.compile(r'Jessica Cadwell?', re.IGNORECASE),
     JOHNNY_EL_HACHEM: re.compile(r'el hachem johnny|johnny el hachem', re.IGNORECASE),
     JOI_ITO: re.compile(r'ji@media.mit.?edu|(joichi|joi)( Ito)?', re.IGNORECASE),
-    JONATHAN_FARKAS: re.compile(r'Jonathan Farka(s|il)', re.IGNORECASE),
+    JONATHAN_FARKAS: re.compile(r'Jonathan Fark(a|u)(s|il)', re.IGNORECASE),
     KATHRYN_RUEMMLER: re.compile(r'Kathr?yn? Ruemmler?', re.IGNORECASE),
     KEN_STARR: re.compile(r'starr, ken|Ken(neth\s*(W.\s*)?)?\s+starr?|starr', re.IGNORECASE),
     LANDON_THOMAS: re.compile(r'lando[nr] thomas( jr)?|thomas jr.?, lando[nr]', re.IGNORECASE),
-    LARRY_SUMMERS: re.compile(r'(La(wrence|rry).{1,5})?Summers?|^LH$|LHS|Ihsofficel', re.IGNORECASE),
+    LARRY_SUMMERS: re.compile(r'(La(wrence|rry).{1,5})?Summers?|^LH$|LHS|[Il]hsofficel?', re.IGNORECASE),
     LAWRANCE_VISOSKI: re.compile(r'La(rry|wrance) Visoski?|Lvjet', re.IGNORECASE),
     LAWRENCE_KRAUSS: re.compile(r'Lawrence Kraus[es]?|[jl]awkrauss|kruase', re.IGNORECASE),
     LEON_BLACK: re.compile(r'Leon\s*Black?|(?<!Marc )Leon(?! (Botstein|Jaworski|Wieseltier))', re.IGNORECASE),
@@ -309,8 +309,47 @@ IRAN_DEAL_RECIPIENTS = ['Allen West', 'Rafael Bardaji', 'Philip Kafka', 'Herb Go
 FLIGHT_IN_2012_PEOPLE = ['Francis Derby', 'Januiz Banasiak', 'Louella Rabuyo', 'Richard Barnnet']
 
 EMAILS_CONFIG = [
+    # 026294 and 026296 might also be Ittihadieh based on timing
     EmailCfg(id='032436', author=ALIREZA_ITTIHADIEH, attribution_reason='Signature'),
+    # 032542 026078 026080 026083 026086 026090 might also be Anas based on discussion of Dubai and Kuwait
     EmailCfg(id='032543', author=ANAS_ALRASHEED, attribution_reason='Later reply 033000 has quote'),
+    EmailCfg(id='026167', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032571', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032573', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032575', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032577', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032579', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032582', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032585', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032588', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032591', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032595', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032599', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032611', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='023661', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032616', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032622', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032628', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='032629', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='032631', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026168', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026170', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026173', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026176', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026180', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026184', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026188', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026193', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026198', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026210', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026204', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='032660', author=ANAS_ALRASHEED, attribution_reason='name visible in 029113 reply'),
+    EmailCfg(id='032663', author=ANAS_ALRASHEED, attribution_reason='name visible in 029113 reply'),
+    EmailCfg(id='032667', author=ANAS_ALRASHEED, attribution_reason='name visible in 029113 reply'),
+    EmailCfg(id='032672', author=ANAS_ALRASHEED, attribution_reason='name visible in 029113 reply'),
+    EmailCfg(id='032676', author=ANAS_ALRASHEED, attribution_reason='name visible in 029113 reply'),
+    EmailCfg(id='026237', author=ANAS_ALRASHEED, attribution_reason='name visible in 029113 reply'),
+    EmailCfg(id='032682', author=ANAS_ALRASHEED, attribution_reason='name visible in 029113 reply'),
     EmailCfg(id='026064', author=ARIANE_DE_ROTHSCHILD, attribution_reason='signature'),
     EmailCfg(id='026069', author=ARIANE_DE_ROTHSCHILD, attribution_reason='signature'),
     EmailCfg(id='030741', author=ARIANE_DE_ROTHSCHILD, attribution_reason='signature'),
@@ -351,6 +390,7 @@ EMAILS_CONFIG = [
         actual_text='',
         author=DARREN_INDYKE,
         description=f"heavily redacted email, quoted replies are from {STEVEN_HOFFENBERG} about James Patterson's book",
+        recipients=['Charles Michael'],
         timestamp=parse('2016-08-17 11:26:00'),
         attribution_reason='Quoted replies are in 019109',
     ),
@@ -444,10 +484,20 @@ EMAILS_CONFIG = [
     EmailCfg(id='017581', author='Lisa Randall', attribution_reason='reply header'),
     EmailCfg(id='026609', author='Mark Green', attribution_reason='Actually a fwd, Mark Green is in signature'),
     EmailCfg(id='030472', author=MARTIN_WEINBERG, attribution_reason='Maybe. in reply', is_attribution_uncertain=True),
+    EmailCfg(id='032563', author=MASHA_DROKOVA, attribution_reason='replied to in 033014'),
+    EmailCfg(id='032564', author=MASHA_DROKOVA, attribution_reason='follow up to 032563 about huffpo article with link'),
+    EmailCfg(id='031544', author=MASHA_DROKOVA, attribution_reason='follow up to 032563 about huffpo article with link'),
+    EmailCfg(id='032605', author=MASHA_DROKOVA, attribution_reason="re: PR interview, 031544 says she'll be in NY at that time"),
+    EmailCfg(id='032606', author=MASHA_DROKOVA, attribution_reason="re: PR interview, 031544 says she'll be in NY at that time"),
+    EmailCfg(id='032607', author=MASHA_DROKOVA, attribution_reason="re: PR interview, 031544 says she'll be in NY at that time"),
+    EmailCfg(id='032609', author=MASHA_DROKOVA, attribution_reason="re: PR interview, 031544 says she'll be in NY at that time"),
+    # 032581, 032604, 033025 may also be Masha based on timing, subject (interviews/articles), and sequential ID
+    EmailCfg(id='032604', author=MASHA_DROKOVA, attribution_reason="timing, subject (interviews/articles), and sequential ID", is_attribution_uncertain=True),
+    EmailCfg(id='032581', author=MASHA_DROKOVA, attribution_reason="timing, subject (interviews/articles), and sequential ID", is_attribution_uncertain=True),
+    EmailCfg(id='033025', author=MASHA_DROKOVA, attribution_reason="timing, subject (interviews/articles), and sequential ID", is_attribution_uncertain=True),
     EmailCfg(id='030235', author=MELANIE_WALKER, attribution_reason='In fwd'),
     EmailCfg(id='032343', author=MELANIE_WALKER, attribution_reason='Name seen in later reply 032346'),
     EmailCfg(id='032212', author=MIROSLAV_LAJCAK, attribution_reason='signature'),
-    EmailCfg(id='022193', author=NADIA_MARCINKO, attribution_reason='reply'),
     EmailCfg(id='021814', author=NADIA_MARCINKO, attribution_reason='reply'),
     EmailCfg(id='021808', author=NADIA_MARCINKO, attribution_reason='reply'),
     EmailCfg(id='022190', author=NADIA_MARCINKO, attribution_reason='reply'),
@@ -508,12 +558,14 @@ EMAILS_CONFIG = [
         author=TERRY_KAFKA,
         fwded_text_after='From: Mike Cohen',
         recipients=cast(list[str | None], [JEFFREY_EPSTEIN, MARK_EPSTEIN, MICHAEL_BUCHHOLTZ] + IRAN_DEAL_RECIPIENTS),
+        subject='Fw: The Iran Nuclear Deal',
         duplicate_ids=['028482'],
     ),
     EmailCfg(id='029992', author=TERRY_KAFKA, attribution_reason='Quoted reply'),
     EmailCfg(id='029985', author=TERRY_KAFKA, attribution_reason='Quoted reply in 029992'),
     EmailCfg(id='020666', author=TERRY_KAFKA, attribution_reason="Ends with 'Terry'"),
     EmailCfg(id='026014', author=ZUBAIR_KHAN, recipients=[JEFFREY_EPSTEIN], timestamp=parse('2016-11-04 17:46:00')),
+    EmailCfg(id='033021', recipients=[ANAS_ALRASHEED], attribution_reason='visible in 033022'),
     EmailCfg(id='027063', recipients=[ANTHONY_BARRETT]),
     EmailCfg(id='030764', recipients=[ARIANE_DE_ROTHSCHILD], attribution_reason='Reply'),
     EmailCfg(id='026431', recipients=[ARIANE_DE_ROTHSCHILD], attribution_reason='Reply'),
@@ -538,6 +590,7 @@ EMAILS_CONFIG = [
     EmailCfg(id='032780', recipients=[JEFFREY_EPSTEIN]),  # Bad OCR (nofix)
     EmailCfg(id='029324', recipients=[JEFFREY_EPSTEIN, "Jojo Fontanilla", "Lyn Fontanilla"]),  # Bad OCR (nofix)
     EmailCfg(id='013482', recipients=[JEFFREY_EPSTEIN], is_fwded_article=True),  # other recipients redacted. "The view from the US: Stem cell therapy steps up a gear with firs"
+    EmailCfg(id='029558', recipients=[JEFFREY_EPSTEIN, KATHERINE_KEATING], attribution_reason='BCC', fwded_text_after='Creativity is central'),
     EmailCfg(id='033456', recipients=["Joel"], attribution_reason='Reply'),
     EmailCfg(id='033458', recipients=["Joel"], attribution_reason='Reply'),
     EmailCfg(id='033460', recipients=["Joel"], attribution_reason='Reply'),
@@ -566,10 +619,13 @@ EMAILS_CONFIG = [
     EmailCfg(id='033466', recipients=[LAWRANCE_VISOSKI], attribution_reason='Reply signature'),
     EmailCfg(id='022250', recipients=[LESLEY_GROFF], attribution_reason='Reply'),
     EmailCfg(id='030242', recipients=[MARIANA_IDZKOWSKA], duplicate_ids=['032048'], dupe_type='redacted'),
+    EmailCfg(id='033027', recipients=[MASHA_DROKOVA], attribution_reason="re: PR interview, 031544 says she'll be in NY at that time"),
     EmailCfg(id='030368', recipients=[MELANIE_SPINELLA], attribution_reason='Actually a self fwd from jeffrey to jeffrey'),
     EmailCfg(id='030369', recipients=[MELANIE_SPINELLA], attribution_reason='Actually a self fwd from jeffrey to jeffrey'),
     EmailCfg(id='030371', recipients=[MELANIE_SPINELLA], attribution_reason='Actually a self fwd from jeffrey to jeffrey'),
     EmailCfg(id='022258', recipients=[NADIA_MARCINKO], attribution_reason='Reply header'),
+    EmailCfg(id='022193', recipients=[NADIA_MARCINKO], attribution_reason='reply'),
+    EmailCfg(id='030572', recipients=[PAULA], attribution_reason='quoted in 030482', is_attribution_uncertain=True),
     EmailCfg(id='030506', recipients=[PAULA], attribution_reason=PAULA_REASON, is_attribution_uncertain=True),
     EmailCfg(id='030507', recipients=[PAULA], attribution_reason=PAULA_REASON, is_attribution_uncertain=True),
     EmailCfg(id='030508', recipients=[PAULA], attribution_reason=PAULA_REASON, is_attribution_uncertain=True),
@@ -585,8 +641,9 @@ EMAILS_CONFIG = [
     EmailCfg(id='032358', actual_text=REDACTED),  # Completely redacted
     EmailCfg(id='033050', actual_text='schwartman'),
     EmailCfg(id='022219', description="discussion of attempts to clean up Epstein's Google search results"),
-    EmailCfg(id='031333', is_fwded_article=True, description='looks like a Russian disinfo article'),  # Russia Says IMF Chief Jailed For Discovering All US Gold is Gone
-    EmailCfg(id='031335', is_fwded_article=True, description='looks like a Russian disinfo article'),  # DOMINQUE STRAUSS-KAHN ARRESTED, NOT BECAUSE HE RAPED A MAID, BUT BECAUSE HE HAD EVIDENCE US HAS NO GOLD IN FORT KNOX.
+    EmailCfg(id='028524', is_fwded_article=True, description='Zach Braff op-ed on Woody Allen in NYT'),
+    EmailCfg(id='031333', is_fwded_article=True, description='Fort Knox conspiracy theory, looks like a Russian disinfo article'),  # Russia Says IMF Chief Jailed For Discovering All US Gold is Gone
+    EmailCfg(id='031335', is_fwded_article=True, description='Fort Knox conspiracy theory, looks like a Russian disinfo article'),  # DOMINQUE STRAUSS-KAHN ARRESTED, NOT BECAUSE HE RAPED A MAID, BUT BECAUSE HE HAD EVIDENCE US HAS NO GOLD IN FORT KNOX.
     EmailCfg(id='023627', is_fwded_article=True, description=MICHAEL_WOLFF_EPSTEIN_ARTICLE_DRAFT),
     EmailCfg(id='026298', is_fwded_article=True, duplicate_ids=['026499']),  # Written by someone else?
     EmailCfg(id='029692', is_fwded_article=True, duplicate_ids=['029779']),  # WaPo article
@@ -640,7 +697,6 @@ EMAILS_CONFIG = [
     EmailCfg(id='031472', is_fwded_article=True),  # WSJ: Lawyers for Imam Wanted by Turkish authorities Fear for Their Client's Life
     EmailCfg(id='012684', is_fwded_article=True),  # Trump in talks to buy socialite Kluge's Charlottesville vineyard
     EmailCfg(id='028536', is_fwded_article=True),  # Palm Beach Post FBI Epstein files say he gave info. Does it explain sweetheart deal?
-    EmailCfg(id='028524', is_fwded_article=True),  # Zach Braff article on Woody Allen in NYT
     EmailCfg(id='030326', is_fwded_article=True),  # NYP Congressional candidate compares Melania Trump to prostitute
     EmailCfg(id='030519', is_fwded_article=True),  # Daily Mail on Prince Andrew
     EmailCfg(id='030878', is_fwded_article=True),  # Steve Bannon almost appeared in Michael Moore's 'Fahrenheit 11/9'
@@ -667,6 +723,7 @@ EMAILS_CONFIG = [
     EmailCfg(id='029841', duplicate_ids=['012711'], dupe_type='redacted'),
     EmailCfg(id='030414', duplicate_ids=['030578'], dupe_type='redacted'),
     EmailCfg(id='031135', duplicate_ids=['030634'], dupe_type='redacted'),
+    EmailCfg(id='030620', duplicate_ids=['023067']),
     EmailCfg(id='029835', duplicate_ids=['028968']),
     EmailCfg(id='033512', duplicate_ids=['033361']),
     EmailCfg(id='030299', duplicate_ids=['021794']),
@@ -768,7 +825,6 @@ EMAILS_CONFIG = [
     # Emails that need a little help determining how to separate the actual text from fwded text
     EmailCfg(id='013415', fwded_text_after='Darren K. Indyke'),
     EmailCfg(id='024624', fwded_text_after='On Tue, May 14'),
-    EmailCfg(id='029558', fwded_text_after='Creativity is central'),
     EmailCfg(id='025888', fwded_text_after='Jul 24, 2015'),
     EmailCfg(id='016413', fwded_text_after='In a former warehouse'),
     EmailCfg(id='025548', fwded_text_after='Edward Jay Epstein'),
@@ -1622,4 +1678,4 @@ REPLY_LINE_ON_NUMERIC_DATE_PATTERN = fr"On \d+/\d+/\d+[, ].*{REPLY_LINE_ENDING_P
 REPLY_LINE_ON_DATE_PATTERN = fr"^On (\d+ )?((Mon|Tues?|Wed(nes)?|Thu(rs)?|Fri|Sat(ur)?|Sun)(day)?|(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)\w*)[, ].*{REPLY_LINE_ENDING_PATTERN}"
 REPLY_LINE_PATTERN = rf"({REPLY_LINE_IN_A_MSG_PATTERN}|{REPLY_LINE_ON_NUMERIC_DATE_PATTERN}|{REPLY_LINE_ON_DATE_PATTERN}|{FORWARDED_LINE_PATTERN})"
 REPLY_REGEX = re.compile(REPLY_LINE_PATTERN, re.IGNORECASE | re.MULTILINE)
-SENT_FROM_REGEX = re.compile(r'^(?:(Please forgive|Sorry for all the) typos.{1,4})?(Sent (from|via).*(and string|AT&T|Droid|iPad|Phone|Mail|BlackBerry(.*(smartphone|device|Handheld|AT&T|T- ?Mobile))?)\.?)', re.M | re.I)
+SENT_FROM_REGEX = re.compile(r'^(?:(Please forgive|Sorry for all the) typos.{1,4})?((Envoyé de mon|Sent (from|via)).*(and string|AT&T|Droid|iPad|Phone|Mail|BlackBerry(.*(smartphone|device|Handheld|AT&T|T- ?Mobile))?)\.?)', re.M | re.I)

epstein_files/util/data.py

@@ -8,6 +8,7 @@ from dateutil import tz
 from typing import TypeVar
 
 from epstein_files.util.constant import names
+from epstein_files.util.constant.strings import QUESTION_MARKS
 from epstein_files.util.env import args
 from epstein_files.util.logging import logger
 
@@ -41,7 +42,7 @@ def extract_last_name(name: str) -> str:
     if ' ' not in name:
         return name
 
-    names = name.split()
+    names = name.removesuffix(QUESTION_MARKS).strip().split()
 
     if names[-1].startswith('Jr') and len(names[-1]) <= 3:
         return ' '.join(names[-2:])
@@ -49,6 +50,13 @@ def extract_last_name(name: str) -> str:
         return names[-1]
 
 
+def extract_first_name(name: str) -> str:
+    if ' ' not in name:
+        return name
+
+    return name.removesuffix(f" {extract_last_name(name)}")
+
+
 def flatten(_list: list[list[T]]) -> list[T]:
     return list(itertools.chain.from_iterable(_list))
 

epstein_files/util/doc_cfg.py

@@ -95,9 +95,13 @@ class DocCfg:
     def complete_description(self) -> str | None:
         """String that summarizes what is known about this document."""
         if self.category and not self.description and not self.author:
-            return self.category
+            if self.category == JUNK:
+                return None
+            else:
+                return self.category
         elif self.category == REPUTATION:
-            return f"{REPUTATION_MGMT}: {self.description}"
+            author_str = f"{self.author} " if self.author else ''
+            return f"{REPUTATION_MGMT}: {author_str}{self.description}"
         elif self.category == SKYPE_LOG:
             msg = f"{self.category} of conversation with {self.author}" if self.author else self.category
             return f"{msg} {self.description}" if self.description else msg
@@ -206,11 +210,13 @@ class EmailCfg(CommunicationCfg):
         fwded_text_after (str | None): If set, any text after this is a fwd of an article or similar
         is_fwded_article (bool): True if this is a newspaper article someone fwded. Used to exclude articles from word counting.
         recipients (list[str | None]): Who received the email
+        subject (str): Subject line
     """
     actual_text: str | None = None
     fwded_text_after: str | None = None
     is_fwded_article: bool = False
     recipients: list[str | None] = field(default_factory=list)
+    subject: str | None = None
 
     # This is necessary because for some dumb reason @dataclass(repr=False) doesn't cut it
     def __repr__(self) -> str:

epstein_files/util/env.py

@@ -5,9 +5,11 @@ from pathlib import Path
 
 from rich_argparse_plus import RichHelpFormatterPlus
 
+from epstein_files.util.constant.output_files import ALL_EMAILS_PATH, CHRONOLOGICAL_EMAILS_PATH, TEXT_MSGS_HTML_PATH
 from epstein_files.util.logging import env_log_level, exit_with_error, logger
 
 DEFAULT_WIDTH = 145
+DEFAULT_FILE = 'default_file'
 EPSTEIN_GENERATE = 'epstein_generate'
 HTML_SCRIPTS = [EPSTEIN_GENERATE, 'epstein_word_count']
 
@@ -34,7 +36,7 @@ parser.add_argument('--overwrite-pickle', '-op', action='store_true', help='re-p
 output = parser.add_argument_group('OUTPUT', 'Options used by epstein_generate.')
 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 an HTML file in docs/')
+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('--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')
@@ -82,6 +84,14 @@ if is_html_script:
         elif not args.email_timeline:
             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
+
+    if args.build == DEFAULT_FILE:
+        if args.all_emails:
+            args.build = ALL_EMAILS_PATH
+        elif args.email_timeline:
+            args.build = CHRONOLOGICAL_EMAILS_PATH
+        else:
+            args.build = TEXT_MSGS_HTML_PATH
 elif parser.prog.startswith('epstein_') and not args.positional_args:
     exit_with_error(f"{parser.prog} requires positional arguments but got none!")
 

epstein_files/util/file_helper.py

@@ -33,10 +33,13 @@ def coerce_file_stem(filename_or_id: int | str) -> str:
 
 
 def extract_file_id(filename_or_id: int | str | Path) -> str:
+    if isinstance(filename_or_id, str):
+        filename_or_id = filename_or_id.removesuffix(',')
+
     if isinstance(filename_or_id, int) or (isinstance(filename_or_id, str) and len(filename_or_id) <= 6):
         return id_str(filename_or_id)
 
-    file_match = FILE_ID_REGEX.match(str(filename_or_id))
+    file_match = FILE_ID_REGEX.match(str(filename_or_id).upper())
 
     if not file_match:
         raise RuntimeError(f"Failed to extract file ID from {filename_or_id}")