[refactor] engines: use datetime.fromisoformat instead of datetime.strptime where possible (#6394)

Refactor engines that parse ISO 8601 dates with strptime to use
fromisoformat instead. In most cases this is a direct replacement of
strptime(text, "format") with fromisoformat(text).

For engines where the source has a trailing "Z" that strptime consumed
as a literal (e.g. "%Y-%m-%dT%H:%M:%S.%fZ" in huggingface.py), add
rstrip("Z") to keep the output naive and preserve the existing behavior.

In sogou.py the date is extracted with a regular expression, which can
yield strings like "2026-7-11". strptime accepts this via its format
string, but fromisoformat does not. To preserve the existing behavior
and satisfy the format fromisoformat expects, add zero-padding for the
month and day.

Closes: #6098
---------
Signed-off-by: OneVth <onebrotravel@gmail.com>

searx/engines/acfun.py

@@ -83,7 +83,7 @@ def extract_video_data(video_block):
         published_date = None
         if create_time:
             try:
-                published_date = datetime.strptime(create_time.strip(), "%Y-%m-%d")
+                published_date = datetime.fromisoformat(create_time.strip())
             except (ValueError, TypeError):
                 pass
 

searx/engines/arxiv.py

@@ -109,7 +109,7 @@ def response(resp: "SXNG_Response") -> EngineResults:
         comments_elements = eval_xpath_getindex(entry, xpath_comment, 0, default=None)
         comments: str = "" if comments_elements is None else comments_elements.text
 
-        publishedDate = datetime.strptime(eval_xpath_getindex(entry, xpath_published, 0).text, "%Y-%m-%dT%H:%M:%SZ")
+        publishedDate = datetime.fromisoformat(eval_xpath_getindex(entry, xpath_published, 0).text.rstrip("Z"))
 
         res.add(
             res.types.Paper(

searx/engines/baidu.py

@@ -186,7 +186,7 @@ def parse_images(data):
             img_date = item.get("bdImgnewsDate")
             publishedDate = None
             if img_date:
-                publishedDate = datetime.strptime(img_date, "%Y-%m-%d %H:%M")
+                publishedDate = datetime.fromisoformat(img_date)
             results.append(
                 {
                     "template": "images.html",

searx/engines/bitchute.py

@@ -44,7 +44,7 @@ def response(resp):
                 "url": 'https://www.bitchute.com/video/' + item['video_id'],
                 "content": html_to_text(item['description']),
                 "author": item['channel']['channel_name'],
-                "publishedDate": datetime.strptime(item["date_published"], "%Y-%m-%dT%H:%M:%S.%fZ"),
+                "publishedDate": datetime.fromisoformat(item["date_published"].rstrip("Z")),
                 "length": item['duration'],
                 "views": item['view_count'],
                 "thumbnail": item['thumbnail_url'],

searx/engines/boardreader.py

@@ -104,7 +104,7 @@ def response(resp: "SXNG_Response") -> EngineResults:
                 title=_remove_keyword_marker(result["Subject"]),
                 content=_remove_keyword_marker(result["Text"]),
                 url=result["Url"],
-                publishedDate=datetime.strptime(result["Published"], "%Y-%m-%d %H:%M:%S"),
+                publishedDate=datetime.fromisoformat(result["Published"]),
                 metadata=gettext.gettext("Posted by {author}").format(author=result["Author"]),
             )
         )

searx/engines/chefkoch.py

@@ -43,7 +43,7 @@ def response(resp):
 
         publishedDate = None
         if recipe['submissionDate']:
-            publishedDate = datetime.strptime(result['recipe']['submissionDate'][:19], "%Y-%m-%dT%H:%M:%S")
+            publishedDate = datetime.fromisoformat(result['recipe']['submissionDate'][:19])
 
         content = [
             f"Schwierigkeitsstufe (1-3): {recipe['difficulty']}",

searx/engines/findthatmeme.py

@@ -37,7 +37,7 @@ def response(resp):
     for item in search_res:
         img = 'https://s3.thehackerblog.com/findthatmeme/' + item['image_path']
         thumb = 'https://s3.thehackerblog.com/findthatmeme/thumb/' + item.get('thumbnail', '')
-        date = datetime.strptime(item["updated_at"].split("T")[0], "%Y-%m-%d")
+        date = datetime.fromisoformat(item["updated_at"].split("T")[0])
         formatted_date = datetime.fromtimestamp(date.timestamp())
 
         results.append(

searx/engines/fyyd.py

@@ -47,7 +47,7 @@ def response(resp: "SXNG_Response"):
                 title=result["title"],
                 content=result["description"],
                 thumbnail=result["smallImageURL"],
-                publishedDate=datetime.strptime(result["status_since"], "%Y-%m-%d %H:%M:%S"),
+                publishedDate=datetime.fromisoformat(result["status_since"]),
                 metadata=f"Rank: {result['rank']} || {result['episode_count']} episodes",
             )
         )

searx/engines/huggingface.py

@@ -91,7 +91,7 @@ def response(resp) -> EngineResults:
 
         published_date = None
         try:
-            published_date = datetime.strptime(entry["createdAt"], "%Y-%m-%dT%H:%M:%S.%fZ")
+            published_date = datetime.fromisoformat(entry["createdAt"].rstrip("Z"))
         except (ValueError, TypeError):
             pass
 

searx/engines/iqiyi.py

@@ -43,7 +43,7 @@ def _result(video: dict[str, typing.Any], album_info: dict[str, typing.Any]):
     release_time = album_info.get("releaseTime", {}).get("value")
     if release_time:
         try:
-            published_date = datetime.strptime(release_time, "%Y-%m-%d")
+            published_date = datetime.fromisoformat(release_time)
         except (ValueError, TypeError):
             pass
 

searx/engines/lemmy.py

@@ -92,7 +92,7 @@ def _get_communities(json):
                 'title': result['community']['title'],
                 'content': markdown_to_text(result['community'].get('description', '')),
                 'thumbnail': result['community'].get('icon', result['community'].get('banner')),
-                'publishedDate': datetime.strptime(counts['published'][:19], '%Y-%m-%dT%H:%M:%S'),
+                'publishedDate': datetime.fromisoformat(counts['published'][:19]),
                 'metadata': metadata,
             }
         )
@@ -141,7 +141,7 @@ def _get_posts(json):
                 'title': result['post']['name'],
                 'content': content,
                 'thumbnail': thumbnail,
-                'publishedDate': datetime.strptime(result['post']['published'][:19], '%Y-%m-%dT%H:%M:%S'),
+                'publishedDate': datetime.fromisoformat(result['post']['published'][:19]),
                 'metadata': metadata,
             }
         )
@@ -170,7 +170,7 @@ def _get_comments(json):
                 'url': result['comment']['ap_id'],
                 'title': result['post']['name'],
                 'content': markdown_to_text(result['comment']['content']),
-                'publishedDate': datetime.strptime(result['comment']['published'][:19], '%Y-%m-%dT%H:%M:%S'),
+                'publishedDate': datetime.fromisoformat(result['comment']['published'][:19]),
                 'metadata': metadata,
             }
         )

searx/engines/mastodon.py

@@ -60,7 +60,7 @@ def response(resp):
                     'title': result['username'] + f" ({result['followers_count']} followers)",
                     'content': result['note'],
                     'thumbnail': result.get('avatar'),
-                    'publishedDate': datetime.strptime(result['created_at'][:10], "%Y-%m-%d"),
+                    'publishedDate': datetime.fromisoformat(result['created_at'][:10]),
                 }
             )
         elif mastodon_type == "hashtags":

searx/engines/nvd.py

@@ -44,7 +44,7 @@ def response(resp) -> EngineResults:
 
         cve_id = item["cve"]["id"]
         description = item["cve"]["descriptions"][0]["value"]
-        date = datetime.strptime(item["cve"]["published"], "%Y-%m-%dT%H:%M:%S.%f")
+        date = datetime.fromisoformat(item["cve"]["published"])
 
         # Extract severity (Low, Medium, High, or Critical) and CVSS score, if available
         info = item["cve"].get("metrics", {}).get("cvssMetricV31", [{}])[0].get("cvssData", {})

searx/engines/odysee.py

@@ -76,7 +76,7 @@ def response(resp):
         release_time = item["release_time"]
         duration = item["duration"]
 
-        release_date = datetime.strptime(release_time.split("T")[0], "%Y-%m-%d")
+        release_date = datetime.fromisoformat(release_time.split("T")[0])
         formatted_date = datetime.fromtimestamp(release_date.timestamp())
 
         url = f"https://odysee.com/{name}:{claim_id}"

searx/engines/podchaser.py

@@ -54,7 +54,7 @@ def response(resp: "SXNG_Response"):
                 title=result["title"],
                 content=result["description"],
                 thumbnail=result["image_url"],
-                publishedDate=datetime.strptime(result["created_at"], "%Y-%m-%d %H:%M:%S"),
+                publishedDate=datetime.fromisoformat(result["created_at"]),
                 metadata=" | ".join(metadata),
             )
         )

searx/engines/quark.py

@@ -292,7 +292,7 @@ def parse_news_uchq(data):
     results = []
     for item in data.get('feed', []):
         try:
-            published_date = datetime.strptime(item.get('time'), "%Y-%m-%d")
+            published_date = datetime.fromisoformat(item.get('time'))
         except (ValueError, TypeError):
             # Sometime Quark will return non-standard format like "1天前", set published_date as None
             published_date = None

searx/engines/rumble.py

@@ -58,7 +58,7 @@ def response(resp):
         title = extract_text(result_dom.xpath(title_xpath))
         p_date = extract_text(result_dom.xpath(published_date))
         # fix offset date for line 644 webapp.py check
-        fixed_date = datetime.strptime(p_date, '%Y-%m-%dT%H:%M:%S%z')
+        fixed_date = datetime.fromisoformat(p_date)
         earned = extract_text(result_dom.xpath(earned_xpath))
         views = extract_text(result_dom.xpath(views_xpath))
         rumbles = extract_text(result_dom.xpath(rumbles_xpath))

searx/engines/semantic_scholar.py

@@ -120,7 +120,7 @@ def response(resp: "SXNG_Response") -> EngineResults:
 
         publishedDate: datetime | None
         if "pubDate" in result:
-            publishedDate = datetime.strptime(result["pubDate"], "%Y-%m-%d")
+            publishedDate = datetime.fromisoformat(result["pubDate"])
         else:
             publishedDate = None
 

searx/engines/sogou.py

@@ -95,7 +95,8 @@ def _parse_date(text):
         date_match = re.search(r"(\d{4}-\d{1,2}-\d{1,2})", text)
         if date_match:
             try:
-                return datetime.strptime(date_match.group(1), "%Y-%m-%d")
+                y, m, d = date_match.group(1).split("-")
+                return datetime(year=int(y), month=int(m), day=int(d))
             except (ValueError, TypeError):
                 pass
     return None

searx/engines/sogou_videos.py

@@ -54,7 +54,7 @@ def response(resp):
         published_date = None
         if entry.get("date") and entry.get("duration"):
             try:
-                published_date = datetime.strptime(entry['date'], "%Y-%m-%d")
+                published_date = datetime.fromisoformat(entry['date'])
             except (ValueError, TypeError):
                 published_date = None
 

searx/engines/springer.py

@@ -134,7 +134,7 @@ def response(resp: "SXNG_Response") -> EngineResults:
         return str(record.get(k, ""))
 
     for record in json_data["records"]:
-        published = datetime.strptime(record["publicationDate"], "%Y-%m-%d")
+        published = datetime.fromisoformat(record["publicationDate"])
         authors: list[str] = [" ".join(author["creator"].split(", ")[::-1]) for author in record["creators"]]
 
         pdf_url = ""

searx/engines/tagesschau.py

@@ -81,7 +81,7 @@ def _story(item):
     return {
         'title': item['title'],
         'thumbnail': item.get('teaserImage', {}).get('imageVariants', {}).get('16x9-256'),
-        'publishedDate': datetime.strptime(item['date'][:19], '%Y-%m-%dT%H:%M:%S'),
+        'publishedDate': datetime.fromisoformat(item['date'][:19]),
         'content': item.get('firstSentence'),
         'url': item['shareURL'] if use_source_url else item['detailsweb'],
     }
@@ -103,7 +103,7 @@ def _video(item):
         'template': 'videos.html',
         'title': title,
         'thumbnail': item.get('teaserImage', {}).get('imageVariants', {}).get('16x9-256'),
-        'publishedDate': datetime.strptime(item['date'][:19], '%Y-%m-%dT%H:%M:%S'),
+        'publishedDate': datetime.fromisoformat(item['date'][:19]),
         'content': item.get('firstSentence', ''),
         'iframe_src': video_url,
         'url': url,

searx/engines/tineye.py

@@ -121,7 +121,7 @@ def parse_tineye_match(match_json):
 
             crawl_date = backlink_json.get("crawl_date")
             if crawl_date:
-                crawl_date = datetime.strptime(crawl_date, '%Y-%m-%d')
+                crawl_date = datetime.fromisoformat(crawl_date)
             else:
                 crawl_date = datetime.min
 

searx/engines/tootfinder.py

@@ -51,7 +51,7 @@ def response(resp):
                 'title': title,
                 'content': html_to_text(result['content']),
                 'thumbnail': thumbnail,
-                'publishedDate': datetime.strptime(result['created_at'], '%Y-%m-%d %H:%M:%S'),
+                'publishedDate': datetime.fromisoformat(result['created_at']),
             }
         )
 

searx/engines/wallhaven.py

@@ -79,7 +79,7 @@ def response(resp):
                 'img_src': result['path'],
                 'thumbnail_src': result['thumbs']['small'],
                 'resolution': result['resolution'].replace('x', ' x '),
-                'publishedDate': datetime.strptime(result['created_at'], '%Y-%m-%d %H:%M:%S'),
+                'publishedDate': datetime.fromisoformat(result['created_at']),
                 'img_format': result['file_type'],
                 'filesize': humanize_bytes(result['file_size']),
             }