From beef5514dda6038f95b65882ae0637393094db4d Mon Sep 17 00:00:00 2001
From: Adrien Barbaresi <barbaresi@bbaw.de>
Date: Thu, 26 Oct 2023 15:38:59 +0200
Subject: [PATCH] simplify further

---
 htmldate/core.py       | 38 ++++++++++++++++++--------------------
 htmldate/extractors.py | 39 +++++++++++++++++++--------------------
 2 files changed, 37 insertions(+), 40 deletions(-)

diff --git a/htmldate/core.py b/htmldate/core.py
index 44145ac3..f7f69cb3 100644
--- a/htmldate/core.py
+++ b/htmldate/core.py
@@ -26,7 +26,7 @@
     img_search,
     json_search,
     regex_parse,
-    timestamp_search,
+    pattern_search,
     try_date_expr,
     DATE_EXPRESSIONS,
     FAST_PREPEND,
@@ -37,6 +37,7 @@
     YEAR_PATTERN,
     YMD_PATTERN,
     COPYRIGHT_PATTERN,
+    TIMESTAMP_PATTERN,
     THREE_PATTERN,
     THREE_CATCH,
     THREE_LOOSE_PATTERN,
@@ -201,14 +202,13 @@ def examine_text(
     max_date: datetime,
 ) -> Optional[str]:
     "Prepare text and try to extract a date."
-    attempt = None
     text = trim_text(text)
-    if len(text) > MIN_SEGMENT_LEN:
-        text = NON_DIGITS_REGEX.sub("", text[:MAX_SEGMENT_LEN])
-        attempt = try_date_expr(
-            text, outputformat, extensive_search, min_date, max_date
-        )
-    return attempt
+
+    if len(text) <= MIN_SEGMENT_LEN:
+        return None
+
+    text = NON_DIGITS_REGEX.sub("", text[:MAX_SEGMENT_LEN])
+    return try_date_expr(text, outputformat, extensive_search, min_date, max_date)
 
 
 def examine_date_elements(
@@ -225,17 +225,13 @@ def examine_date_elements(
         return None
 
     for elem in elements:
-        attempt = examine_text(
-            elem.text_content(), outputformat, extensive_search, min_date, max_date
-        )
-        if attempt:
-            return attempt
-        # try link title (Blogspot)
-        attempt = examine_text(
-            elem.get("title", ""), outputformat, extensive_search, min_date, max_date
-        )
-        if attempt:
-            return attempt
+        # try element text and link title (Blogspot)
+        for text in [elem.text_content(), elem.get("title", "")]:
+            attempt = examine_text(
+                text, outputformat, extensive_search, min_date, max_date
+            )
+            if attempt:
+                return attempt
 
     return None
 
@@ -1091,7 +1087,9 @@ def find_date(
         htmlstring = tostring(search_tree, pretty_print=False).decode("utf-8", "ignore")
 
     # date regex timestamp rescue
-    timestamp_result = timestamp_search(htmlstring, outputformat, min_date, max_date)
+    timestamp_result = pattern_search(
+        htmlstring, TIMESTAMP_PATTERN, outputformat, min_date, max_date
+    )
     if timestamp_result is not None:
         return timestamp_result
 
diff --git a/htmldate/extractors.py b/htmldate/extractors.py
index cfb1ebcc..d3cd346b 100644
--- a/htmldate/extractors.py
+++ b/htmldate/extractors.py
@@ -12,7 +12,7 @@
 
 from datetime import datetime
 from functools import lru_cache
-from typing import List, Optional, Tuple
+from typing import List, Optional, Pattern, Tuple
 
 # coverage for date parsing
 from dateparser import DateDataParser  # type: ignore  # third-party, slow
@@ -463,6 +463,23 @@ def img_search(
     return None
 
 
+def pattern_search(
+    text: str,
+    date_pattern: Pattern[str],
+    outputformat: str,
+    min_date: datetime,
+    max_date: datetime,
+) -> Optional[str]:
+    "Look for date expressions using a regular expression on a string of text."
+    match = date_pattern.search(text)
+    if match and is_valid_date(
+        match[1], "%Y-%m-%d", earliest=min_date, latest=max_date
+    ):
+        LOGGER.debug("regex found: %s %s", date_pattern, match[0])
+        return convert_date(match[1], "%Y-%m-%d", outputformat)
+    return None
+
+
 def json_search(
     tree: HtmlElement,
     outputformat: str,
@@ -479,25 +496,7 @@ def json_search(
     ):
         if not elem.text or '"date' not in elem.text:
             continue
-        json_match = json_pattern.search(elem.text)
-        if json_match and is_valid_date(
-            json_match[1], "%Y-%m-%d", earliest=min_date, latest=max_date
-        ):
-            LOGGER.debug("JSON time found: %s", json_match[0])
-            return convert_date(json_match[1], "%Y-%m-%d", outputformat)
-    return None
-
-
-def timestamp_search(
-    htmlstring: str, outputformat: str, min_date: datetime, max_date: datetime
-) -> Optional[str]:
-    """Look for timestamps throughout the web page"""
-    tstamp_match = TIMESTAMP_PATTERN.search(htmlstring)
-    if tstamp_match and is_valid_date(
-        tstamp_match[1], "%Y-%m-%d", earliest=min_date, latest=max_date
-    ):
-        LOGGER.debug("time regex found: %s", tstamp_match[0])
-        return convert_date(tstamp_match[1], "%Y-%m-%d", outputformat)
+        return pattern_search(elem.text, json_pattern, outputformat, min_date, max_date)
     return None