'Refactored by Sourcery'

htmldate/core.py

@@ -218,19 +218,17 @@ def examine_date_elements(
                 "analyzing (HTML): %s",
                 " ".join(logstring(elem).split())[:100],
             )
-            attempt = try_date_expr(
+            if attempt := try_date_expr(
                 text, outputformat, extensive_search, min_date, max_date
-            )
-            if attempt:
+            ):
                 return attempt
         # try link title (Blogspot)
         title_attr = trim_text(elem.get("title", ""))
         if len(title_attr) > MIN_SEGMENT_LEN:
             title_attr = NON_DIGITS_REGEX.sub("", title_attr[:MAX_SEGMENT_LEN])
-            attempt = try_date_expr(
+            if attempt := try_date_expr(
                 title_attr, outputformat, extensive_search, min_date, max_date
-            )
-            if attempt:
+            ):
                 return attempt
 
     return None
@@ -404,8 +402,7 @@ def select_candidate(
     years = [""] * len(bestones)
     validation = [False] * len(bestones)
     for i, pattern in enumerate(patterns):
-        year_match = yearpat.search(pattern)
-        if year_match:
+        if year_match := yearpat.search(pattern):
             years[i] = year_match[1]
             dateobject = datetime(int(year_match[1]), 1, 1)
             validation[i] = date_validator(
@@ -642,7 +639,7 @@ def normalize_match(match: Optional[Match[str]]) -> str:
     and optionally expand the year from two to four digits."""
     day, month, year = (g.zfill(2) for g in match.groups() if g)  # type: ignore[union-attr]
     if len(year) == 2:
-        year = "19" + year if year[0] == "9" else "20" + year
+        year = f"19{year}" if year[0] == "9" else f"20{year}"
     return f"{year}-{month}-{day}"
 
 
@@ -870,7 +867,7 @@ def search_page(
         match = TWO_COMP_REGEX.match(item)
         month = match[1]  # type: ignore[index]
         if len(month) == 1:
-            month = "0" + month
+            month = f"0{month}"
         candidate = "-".join([match[2], month, "01"])  # type: ignore[index]
         replacement[candidate] = candidates[item]
     candidates = Counter(replacement)
@@ -923,9 +920,11 @@ def search_page(
     if bestmatch is not None:
         dateobject = datetime(int(bestmatch[0]), 1, 1)
         if (
-            date_validator(dateobject, "%Y-%m-%d", earliest=min_date, latest=max_date)
+            date_validator(
+                dateobject, "%Y-%m-%d", earliest=min_date, latest=max_date
+            )
             is True
-            and int(dateobject.year) >= copyear
+            and dateobject.year >= copyear
         ):
             LOGGER.debug(
                 'date found for pattern "%s": %s', SIMPLE_PATTERN, bestmatch[0]

htmldate/extractors.py

@@ -3,6 +3,7 @@
 Custom parsers and XPath expressions for date extraction
 """
 
+
 ## This file is available from https://github.com/adbar/htmldate
 ## under GNU GPL v3 license
 
@@ -85,7 +86,7 @@
 # or contains(@class, 'article')
 # or contains(@id, 'lastmod') or contains(@class, 'updated')
 
-FREE_TEXT_EXPRESSIONS = FAST_PREPEND + "/text()"
+FREE_TEXT_EXPRESSIONS = f"{FAST_PREPEND}/text()"
 MIN_SEGMENT_LEN = 6
 MAX_SEGMENT_LEN = 52
 
@@ -230,8 +231,7 @@ def extract_url_date(
     testurl: str, outputformat: str, min_date: datetime, max_date: datetime
 ) -> Optional[str]:
     """Extract the date out of an URL string complying with the Y-M-D format"""
-    match = COMPLETE_URL.search(testurl)
-    if match:
+    if match := COMPLETE_URL.search(testurl):
         LOGGER.debug("found date in URL: %s", match[0])
         try:
             dateobject = datetime(int(match[1]), int(match[2]), int(match[3]))
@@ -326,9 +326,7 @@ def custom_parse(
             LOGGER.debug("parsing result: %s", candidate)
             return candidate.strftime(outputformat)
 
-    # 2. Try YYYYMMDD, use regex
-    match = YMD_NO_SEP_PATTERN.search(string)
-    if match:
+    if match := YMD_NO_SEP_PATTERN.search(string):
         try:
             year, month, day = int(match[1][:4]), int(match[1][4:6]), int(match[1][6:8])
             candidate = datetime(year, month, day)
@@ -344,9 +342,7 @@ def custom_parse(
                 LOGGER.debug("YYYYMMDD match: %s", candidate)
                 return candidate.strftime(outputformat)
 
-    # 3. Try the very common YMD, Y-M-D, and D-M-Y patterns
-    match = YMD_PATTERN.search(string)
-    if match:
+    if match := YMD_PATTERN.search(string):
         try:
             if match.lastgroup == "day":
                 year, month, day = (
@@ -373,9 +369,7 @@ def custom_parse(
                 LOGGER.debug("regex match: %s", candidate)
                 return candidate.strftime(outputformat)
 
-    # 4. Try the Y-M and M-Y patterns
-    match = YM_PATTERN.search(string)
-    if match:
+    if match := YM_PATTERN.search(string):
         try:
             if match.lastgroup == "month":
                 candidate = datetime(
@@ -524,14 +518,13 @@ def idiosyncrasies_search(
     htmlstring: str, outputformat: str, min_date: datetime, max_date: datetime
 ) -> Optional[str]:
     """Look for author-written dates throughout the web page"""
-    match = TEXT_PATTERNS.search(htmlstring)  # EN+DE+TR
-    if match:
+    if match := TEXT_PATTERNS.search(htmlstring):
         parts = list(filter(None, match.groups()))
         if len(parts) == 3:
             candidate = None
             if len(parts[0]) == 4:
                 candidate = datetime(int(parts[0]), int(parts[1]), int(parts[2]))
-            elif len(parts[2]) in (2, 4):
+            elif len(parts[2]) in {2, 4}:
                 # DD/MM/YY
                 day, month = try_swap_values(int(parts[0]), int(parts[1]))
                 year = correct_year(int(parts[2]))