scitex 2.5.0__py3-none-any.whl → 2.7.0__py3-none-any.whl

scitex/scholar/url_finder/translators/individual/archive_ouverte_en_sciences_de_l_information_et_de_la_communication___aosic_.py

@@ -8,10 +8,14 @@ from playwright.async_api import Page
 from ..core.base import BaseTranslator
 
 
-class ArchiveOuverteEnSciencesDeLInformationEtDeLaCommunicationAosicTranslator(BaseTranslator):
+class ArchiveOuverteEnSciencesDeLInformationEtDeLaCommunicationAosicTranslator(
+    BaseTranslator
+):
     """Archive Ouverte en Sciences de l'Information et de la Communication  (AOSIC)."""
 
-    LABEL = "Archive Ouverte en Sciences de l'Information et de la Communication  (AOSIC)"
+    LABEL = (
+        "Archive Ouverte en Sciences de l'Information et de la Communication  (AOSIC)"
+    )
     URL_TARGET_PATTERN = r"^https?://archivesic\.ccsd\.cnrs\.fr/"
 
     @classmethod

scitex/scholar/url_finder/translators/individual/artforum.py

@@ -19,14 +19,14 @@ TRANSLATOR_INFO = {
     "in_repository": True,
     "translator_type": 4,
     "browser_support": "gcsibv",
-    "last_updated": "2021-09-02 00:33:38"
+    "last_updated": "2021-09-02 00:33:38",
 }
 
 
 def detect_web(doc: Any, url: str) -> Optional[str]:
     """Detect if the page is a single item or multiple items"""
-    if re.search(r'-\d{5,}([?#].*)?$', url):
-        if doc.select_one('h3.print-article__issue-title'):
+    if re.search(r"-\d{5,}([?#].*)?$", url):
+        if doc.select_one("h3.print-article__issue-title"):
             return "magazineArticle"
         return "blogPost"
     elif get_search_results(doc, check_only=True):
@@ -37,22 +37,24 @@ def detect_web(doc: Any, url: str) -> Optional[str]:
 def get_search_results(doc: Any, check_only: bool = False) -> Optional[Dict[str, str]]:
     """Get search results from a multiple item page"""
     items = {}
-    rows = doc.select('h1.results-list__h1, .toc-article__title, .news-list h1, '
-                     '.reviews-list h1, .article-list h1, p.hp-singlefeature-author__writer, '
-                     'h3.hp-news__title, h3.hp-twocolumn__title a, h3.hp-artguide__title, '
-                     'p.hp-bloglist__teaser a')
+    rows = doc.select(
+        "h1.results-list__h1, .toc-article__title, .news-list h1, "
+        ".reviews-list h1, .article-list h1, p.hp-singlefeature-author__writer, "
+        "h3.hp-news__title, h3.hp-twocolumn__title a, h3.hp-artguide__title, "
+        "p.hp-bloglist__teaser a"
+    )
 
     for row in rows:
-        link = row.select_one('a')
+        link = row.select_one("a")
         if not link:
-            link = row if row.name == 'a' else None
+            link = row if row.name == "a" else None
             if not link:
-                parent = row.find_parent('a')
+                parent = row.find_parent("a")
                 if parent:
                     link = parent
 
         if link:
-            href = link.get('href')
+            href = link.get("href")
             title = row.get_text(strip=True)
             if href and title:
                 if check_only:
@@ -77,7 +79,7 @@ def scrape(doc: Any, url: str) -> Dict[str, Any]:
         "attachments": [{"title": "Snapshot", "mimeType": "text/html"}],
         "tags": [],
         "notes": [],
-        "seeAlso": []
+        "seeAlso": [],
     }
 
     # Try to get data from JSON-LD
@@ -86,43 +88,49 @@ def scrape(doc: Any, url: str) -> Dict[str, Any]:
         try:
             json_data = json.loads(json_ld_tag.string)
             item["title"] = json_data.get("name", "")
-            item["date"] = json_data.get("dateModified") or json_data.get("datePublished", "")
+            item["date"] = json_data.get("dateModified") or json_data.get(
+                "datePublished", ""
+            )
 
             if not item["creators"] and json_data.get("author"):
                 author_name = json_data["author"].get("name", "")
                 if author_name:
                     parts = author_name.split()
                     if len(parts) > 1:
-                        item["creators"].append({
-                            "firstName": " ".join(parts[:-1]),
-                            "lastName": parts[-1],
-                            "creatorType": "author"
-                        })
+                        item["creators"].append(
+                            {
+                                "firstName": " ".join(parts[:-1]),
+                                "lastName": parts[-1],
+                                "creatorType": "author",
+                            }
+                        )
         except (json.JSONDecodeError, KeyError):
             pass
 
     # Get authors from metadata
-    author_links = doc.select('.contrib-link a')
+    author_links = doc.select(".contrib-link a")
     for link in author_links:
         author_name = link.get_text(strip=True)
         parts = author_name.split()
         if len(parts) > 1:
-            item["creators"].append({
-                "firstName": " ".join(parts[:-1]),
-                "lastName": parts[-1],
-                "creatorType": "author"
-            })
+            item["creators"].append(
+                {
+                    "firstName": " ".join(parts[:-1]),
+                    "lastName": parts[-1],
+                    "creatorType": "author",
+                }
+            )
 
     # Handle magazine articles
     if item_type == "magazineArticle":
         item["ISSN"] = "0004-3532"
-        issue_date_elem = doc.select_one('h3.print-article__issue-title')
+        issue_date_elem = doc.select_one("h3.print-article__issue-title")
         if issue_date_elem:
-            date_text = issue_date_elem.get_text(strip=True).replace('PRINT ', '')
+            date_text = issue_date_elem.get_text(strip=True).replace("PRINT ", "")
             item["date"] = date_text
 
             # Try to get volume and issue from linked page
-            issue_link = issue_date_elem.select_one('a')
+            issue_link = issue_date_elem.select_one("a")
             if issue_link:
                 # Note: In a real implementation, you would fetch this page
                 # and extract volume/issue. For now, we'll leave them empty

scitex/scholar/url_finder/translators/individual/arxiv.py

@@ -30,7 +30,7 @@ class ArXivTranslator(BaseTranslator):
 
         # Extract arXiv ID from URL
         # Matches: /abs/2308.09312 or /pdf/2308.09312
-        match = re.search(r'/(abs|pdf)/(\d+\.\d+)', url)
+        match = re.search(r"/(abs|pdf)/(\d+\.\d+)", url)
         if match:
             arxiv_id = match.group(2)
             pdf_url = f"https://arxiv.org/pdf/{arxiv_id}.pdf"

scitex/scholar/url_finder/translators/individual/arxiv_org.py

@@ -57,8 +57,8 @@ class ArXivOrgTranslator(BaseTranslator):
         # Handle direct PDF pages
         if "/pdf/" in url:
             # Already on a PDF page - ensure it has .pdf extension
-            if not url.endswith('.pdf'):
-                url = url + '.pdf'
+            if not url.endswith(".pdf"):
+                url = url + ".pdf"
             pdf_urls.append(url)
             return pdf_urls
 
@@ -90,14 +90,18 @@ class ArXivOrgTranslator(BaseTranslator):
                         href = await link_elem.get_attribute("href")
                         if href:
                             # Extract arXiv ID
-                            arxiv_id = href.strip().replace("arXiv:", "").replace("/abs/", "")
+                            arxiv_id = (
+                                href.strip().replace("arXiv:", "").replace("/abs/", "")
+                            )
                             pdf_url = f"https://arxiv.org/pdf/{arxiv_id}.pdf"
                             pdf_urls.append(pdf_url)
 
             # Legacy search, listings, and catchup pages
             elif any(pattern in url for pattern in ["/find/", "/list/", "/catchup"]):
                 # Find all abstract links in <dt> elements
-                dt_elements = await page.query_selector_all("#dlpage dt a[title='Abstract']")
+                dt_elements = await page.query_selector_all(
+                    "#dlpage dt a[title='Abstract']"
+                )
                 for link_elem in dt_elements:
                     href = await link_elem.get_attribute("href")
                     if href:

scitex/scholar/url_finder/translators/individual/atlanta_journal_constitution.py

@@ -19,14 +19,16 @@ TRANSLATOR_INFO = {
     "in_repository": True,
     "translator_type": 4,
     "browser_support": "gcsibv",
-    "last_updated": "2021-07-14 19:41:44"
+    "last_updated": "2021-07-14 19:41:44",
 }
 
 
 def detect_web(doc: Any, url: str) -> Optional[str]:
     """Detect if the page is a single item or multiple items"""
-    if doc.select_one('.c-articleContent') and doc.select_one('script[type="application/ld+json"]'):
-        if 'blog/' in url:
+    if doc.select_one(".c-articleContent") and doc.select_one(
+        'script[type="application/ld+json"]'
+    ):
+        if "blog/" in url:
             return "blogPost"
         else:
             return "newspaperArticle"
@@ -38,10 +40,10 @@ def detect_web(doc: Any, url: str) -> Optional[str]:
 def get_search_results(doc: Any, check_only: bool = False) -> Optional[Dict[str, str]]:
     """Get search results from a multiple item page"""
     items = {}
-    rows = doc.select('a.gs-title')
+    rows = doc.select("a.gs-title")
 
     for row in rows:
-        href = row.get('href')
+        href = row.get("href")
         title = row.get_text(strip=True)
         if href and title:
             if check_only:
@@ -53,13 +55,13 @@ def get_search_results(doc: Any, check_only: bool = False) -> Optional[Dict[str,
 
 def extract_place(lead_text: str) -> str:
     """Extract place from lead text"""
-    place_re = re.compile(r'^\s*([A-Z\-\']{3,})\b')
+    place_re = re.compile(r"^\s*([A-Z\-\']{3,})\b")
     match = place_re.search(lead_text)
     if match:
         place = match.group(1)
         # Capitalize properly
         return place.title()
-    return ''
+    return ""
 
 
 def scrape(doc: Any, url: str) -> Dict[str, Any]:
@@ -73,7 +75,7 @@ def scrape(doc: Any, url: str) -> Dict[str, Any]:
     except (json.JSONDecodeError, AttributeError):
         return {}
 
-    item_type = "blogPost" if 'blog/' in url else "newspaperArticle"
+    item_type = "blogPost" if "blog/" in url else "newspaperArticle"
 
     item = {
         "itemType": item_type,
@@ -86,13 +88,13 @@ def scrape(doc: Any, url: str) -> Dict[str, Any]:
         "attachments": [{"title": "Snapshot", "mimeType": "text/html"}],
         "tags": [],
         "notes": [],
-        "seeAlso": []
+        "seeAlso": [],
     }
 
     # Get abstract
     description_tag = doc.select_one('meta[name="description"]')
     item["abstractNote"] = json_data.get("description") or (
-        description_tag.get('content') if description_tag else ""
+        description_tag.get("content") if description_tag else ""
     )
 
     # Extract place from abstract
@@ -100,7 +102,7 @@ def scrape(doc: Any, url: str) -> Dict[str, Any]:
         item["place"] = extract_place(item["abstractNote"])
 
     # Get section label
-    section_label = doc.select_one('.section-label')
+    section_label = doc.select_one(".section-label")
     section_text = section_label.get_text(strip=True) if section_label else ""
 
     if item_type == "blogPost":
@@ -113,19 +115,21 @@ def scrape(doc: Any, url: str) -> Dict[str, Any]:
     # Get language
     language_tag = doc.select_one('meta[name="language"]')
     if language_tag:
-        item["language"] = language_tag.get('content', "English")
+        item["language"] = language_tag.get("content", "English")
 
     # Get authors
     if json_data.get("author") and json_data["author"].get("name"):
-        author_names = json_data["author"]["name"].split(', ')
+        author_names = json_data["author"]["name"].split(", ")
         for author_name in author_names:
             parts = author_name.split()
             if len(parts) > 1:
-                item["creators"].append({
-                    "firstName": " ".join(parts[:-1]),
-                    "lastName": parts[-1],
-                    "creatorType": "author"
-                })
+                item["creators"].append(
+                    {
+                        "firstName": " ".join(parts[:-1]),
+                        "lastName": parts[-1],
+                        "creatorType": "author",
+                    }
+                )
 
     return item
 

scitex/scholar/url_finder/translators/individual/atypon_journals.py

@@ -70,7 +70,9 @@ class AtyponJournalsTranslator(BaseTranslator):
     NEED_BYPASS_EMBEDDED_READER = re.compile(r"^https?://www\.embopress\.org/")
 
     # URL pattern for replacing article view paths with PDF paths
-    REPL_URL_REGEXP = re.compile(r"/doi/((?:abs|abstract|full|figure|ref|citedby|book)/)?")
+    REPL_URL_REGEXP = re.compile(
+        r"/doi/((?:abs|abstract|full|figure|ref|citedby|book)/)?"
+    )
 
     @classmethod
     def matches_url(cls, url: str) -> bool:
@@ -85,7 +87,9 @@ class AtyponJournalsTranslator(BaseTranslator):
         return bool(re.match(cls.URL_TARGET_PATTERN, url))
 
     @classmethod
-    def _build_pdf_url(cls, url: str, has_pdf_link: bool, pdf_path: str) -> Optional[str]:
+    def _build_pdf_url(
+        cls, url: str, has_pdf_link: bool, pdf_path: str
+    ) -> Optional[str]:
         """Build PDF URL from article URL.
 
         Based on JavaScript buildPdfUrl() function (lines 194-223).
@@ -108,8 +112,8 @@ class AtyponJournalsTranslator(BaseTranslator):
 
         # Special case: EMBO Press needs embedded reader bypass
         if cls.NEED_BYPASS_EMBEDDED_READER.match(url):
-            pdf_url = re.sub(r'/e?pdf/', '/pdfdirect/', pdf_url)
-            separator = '&' if '?' in pdf_url else '?'
+            pdf_url = re.sub(r"/e?pdf/", "/pdfdirect/", pdf_url)
+            separator = "&" if "?" in pdf_url else "?"
             pdf_url = f"{pdf_url}{separator}download=true"
 
         return pdf_url
@@ -140,7 +144,7 @@ class AtyponJournalsTranslator(BaseTranslator):
             pass
 
         # PDF paths to try (line 197 + pdfdirect for Neurology and similar)
-        pdf_paths = ['/doi/pdfdirect/', '/doi/pdf/', '/doi/epdf/', '/doi/pdfplus/']
+        pdf_paths = ["/doi/pdfdirect/", "/doi/pdf/", "/doi/epdf/", "/doi/pdfplus/"]
 
         # Try each PDF path pattern
         for pdf_path in pdf_paths:
@@ -150,14 +154,14 @@ class AtyponJournalsTranslator(BaseTranslator):
 
                 if pdf_link:
                     # Try to get href directly from link
-                    href = await pdf_link.get_attribute('href')
+                    href = await pdf_link.get_attribute("href")
                     if href:
                         # Make absolute URL if needed
-                        if href.startswith('http'):
+                        if href.startswith("http"):
                             pdf_urls.append(href)
                         else:
                             # Construct absolute URL
-                            base_url = re.match(r'^https?://[^/]+', url)
+                            base_url = re.match(r"^https?://[^/]+", url)
                             if base_url:
                                 abs_url = base_url.group(0) + href
                                 pdf_urls.append(abs_url)
@@ -178,7 +182,7 @@ class AtyponJournalsTranslator(BaseTranslator):
                 # Check for citation_pdf_url meta tag
                 pdf_meta = await page.query_selector('meta[name="citation_pdf_url"]')
                 if pdf_meta:
-                    content = await pdf_meta.get_attribute('content')
+                    content = await pdf_meta.get_attribute("content")
                     if content:
                         pdf_urls.append(content)
             except Exception:
@@ -211,7 +215,9 @@ if __name__ == "__main__":
 
         for test_url in test_urls:
             print(f"\nTesting AtyponJournalsTranslator with URL: {test_url}")
-            print(f"URL matches pattern: {AtyponJournalsTranslator.matches_url(test_url)}")
+            print(
+                f"URL matches pattern: {AtyponJournalsTranslator.matches_url(test_url)}"
+            )
 
             if not AtyponJournalsTranslator.matches_url(test_url):
                 print("  URL doesn't match Atypon pattern, skipping...")
@@ -228,7 +234,9 @@ if __name__ == "__main__":
                     await page.wait_for_load_state("domcontentloaded")
 
                     print("  Extracting PDF URLs...")
-                    pdf_urls = await AtyponJournalsTranslator.extract_pdf_urls_async(page)
+                    pdf_urls = await AtyponJournalsTranslator.extract_pdf_urls_async(
+                        page
+                    )
 
                     print(f"  Found {len(pdf_urls)} PDF URL(s)")
                     for url in pdf_urls:

scitex/scholar/url_finder/translators/individual/austlii_and_nzlii.py

@@ -19,7 +19,7 @@ TRANSLATOR_INFO = {
     "in_repository": True,
     "translator_type": 4,
     "browser_support": "gcsibv",
-    "last_updated": "2024-11-21 18:54:11"
+    "last_updated": "2024-11-21 18:54:11",
 }
 
 
@@ -36,30 +36,30 @@ JURISDICTION_ABBREV = {
     "TAS": "Tas",
     "Victoria": "Vic",
     "VIC": "Vic",
-    "Western Australia": "WA"
+    "Western Australia": "WA",
 }
 
 
 def detect_web(doc: Any, url: str) -> Optional[str]:
     """Detect if the page is a case, statute, journal article or multiple items"""
-    body = doc.select_one('body')
+    body = doc.select_one("body")
     if body:
-        classes = body.get('class', [])
+        classes = body.get("class", [])
         if isinstance(classes, str):
             classes = classes.split()
 
-        if 'case' in classes:
+        if "case" in classes:
             return "case"
-        if 'legislation' in classes:
+        if "legislation" in classes:
             return "statute"
-        if 'journals' in classes:
+        if "journals" in classes:
             return "journalArticle"
 
-    if 'nzlii.org/nz/cases/' in url and url.endswith('.html'):
+    if "nzlii.org/nz/cases/" in url and url.endswith(".html"):
         return "case"
-    if 'austlii.edu.au/cgi-bin/sinodisp/au/cases/' in url and url.endswith('.html'):
+    if "austlii.edu.au/cgi-bin/sinodisp/au/cases/" in url and url.endswith(".html"):
         return "case"
-    if 'classic.austlii.edu.au' in url and url.endswith('.html'):
+    if "classic.austlii.edu.au" in url and url.endswith(".html"):
         return "case"
 
     if get_search_results(doc, check_only=True):
@@ -71,12 +71,12 @@ def detect_web(doc: Any, url: str) -> Optional[str]:
 def get_search_results(doc: Any, check_only: bool = False) -> Optional[Dict[str, str]]:
     """Get search results from a multiple item page"""
     items = {}
-    rows = doc.select('#page-main ul > li > a')
+    rows = doc.select("#page-main ul > li > a")
 
     for row in rows:
-        href = row.get('href')
+        href = row.get("href")
         title = row.get_text(strip=True)
-        if href and title and '.html' in href:
+        if href and title and ".html" in href:
             if check_only:
                 return True
             items[href] = title
@@ -86,7 +86,7 @@ def get_search_results(doc: Any, check_only: bool = False) -> Optional[Dict[str,
 
 def capitalize_with_punctuation(text: str) -> str:
     """Capitalize text while preserving parenthetical structures"""
-    act_name_delim_regex = re.compile(r'( \(|\) )')
+    act_name_delim_regex = re.compile(r"( \(|\) )")
     words = act_name_delim_regex.split(text)
 
     result = []
@@ -97,12 +97,12 @@ def capitalize_with_punctuation(text: str) -> str:
             # Simple title case
             result.append(word.lower().title())
 
-    return ''.join(result)
+    return "".join(result)
 
 
 def parse_act_name(name_of_act: str) -> Dict[str, str]:
     """Parse act name to extract name and year"""
-    parts = re.split(r'\s(\d{4})', name_of_act)
+    parts = re.split(r"\s(\d{4})", name_of_act)
     if len(parts) >= 2:
         act_name = capitalize_with_punctuation(parts[0])
         act_year = parts[1]
@@ -120,15 +120,17 @@ def scrape(doc: Any, url: str) -> Dict[str, Any]:
         "itemType": item_type,
         "title": "",
         "creators": [],
-        "url": url.replace('http://', 'https://').replace(re.compile(r'^(https://www)\d'), r'\1'),
+        "url": url.replace("http://", "https://").replace(
+            re.compile(r"^(https://www)\d"), r"\1"
+        ),
         "attachments": [{"title": "Snapshot", "mimeType": "text/html"}],
         "tags": [],
         "notes": [],
-        "seeAlso": []
+        "seeAlso": [],
     }
 
     # Get jurisdiction
-    jurisdiction_elem = doc.select_one('li.ribbon-jurisdiction > a > span')
+    jurisdiction_elem = doc.select_one("li.ribbon-jurisdiction > a > span")
     if jurisdiction_elem:
         full_jurisdiction = jurisdiction_elem.get_text(strip=True)
         jurisdiction = JURISDICTION_ABBREV.get(full_jurisdiction, full_jurisdiction)
@@ -136,40 +138,40 @@ def scrape(doc: Any, url: str) -> Dict[str, Any]:
             item["code"] = jurisdiction
 
     # Get citation
-    citation_elem = doc.select_one('li.ribbon-citation > a > span')
+    citation_elem = doc.select_one("li.ribbon-citation > a > span")
     citation = citation_elem.get_text(strip=True) if citation_elem else ""
 
-    ribbon = doc.select_one('#ribbon')
+    ribbon = doc.select_one("#ribbon")
     if ribbon:
         if item_type == "case":
-            title_tag = doc.select_one('head > title')
+            title_tag = doc.select_one("head > title")
             if title_tag:
                 vol_iss = title_tag.get_text(strip=True)
                 # Remove everything after the bracket and date
-                item["caseName"] = re.sub(r'\s?\[.*$', '', vol_iss)
+                item["caseName"] = re.sub(r"\s?\[.*$", "", vol_iss)
                 item["title"] = item["caseName"]
 
                 # Extract date
-                last_paren = re.search(r'\(([^)]*)\)$', vol_iss)
+                last_paren = re.search(r"\(([^)]*)\)$", vol_iss)
                 if last_paren:
                     item["dateDecided"] = last_paren.group(1)
                 else:
-                    year_elem = doc.select_one('li.ribbon-year > a > span')
+                    year_elem = doc.select_one("li.ribbon-year > a > span")
                     if year_elem:
                         item["dateDecided"] = year_elem.get_text(strip=True)
 
             # Get court
-            court_match = re.search(r'/cases/[^/]+/([^/]+)/', url)
+            court_match = re.search(r"/cases/[^/]+/([^/]+)/", url)
             if court_match:
                 item["court"] = court_match.group(1)
             else:
-                court_elem = doc.select_one('li.ribbon-database > a > span')
+                court_elem = doc.select_one("li.ribbon-database > a > span")
                 if court_elem:
                     item["court"] = court_elem.get_text(strip=True)
 
             # Get docket number
             if citation:
-                last_number = re.search(r'(\d+)$', citation)
+                last_number = re.search(r"(\d+)$", citation)
                 if last_number:
                     item["docketNumber"] = last_number.group(1)
 
@@ -180,51 +182,53 @@ def scrape(doc: Any, url: str) -> Dict[str, Any]:
                 item["dateEnacted"] = act_info["actYear"]
 
             # Get section
-            section_elem = doc.select_one('li.ribbon-subject > a > span')
+            section_elem = doc.select_one("li.ribbon-subject > a > span")
             if section_elem:
                 section = section_elem.get_text(strip=True)
-                item["section"] = section.replace('SECT ', '')
+                item["section"] = section.replace("SECT ", "")
 
         elif item_type == "journalArticle":
-            title_tag = doc.select_one('title')
+            title_tag = doc.select_one("title")
             if title_tag:
                 title_text = title_tag.get_text(strip=True)
                 match = re.search(r'(.*) --- "([^"]*)"', title_text)
                 if match:
                     item["title"] = match.group(2)
-                    authors = match.group(1).split(';')
+                    authors = match.group(1).split(";")
                     for author in authors:
                         parts = author.strip().split()
                         if len(parts) > 1:
-                            item["creators"].append({
-                                "firstName": " ".join(parts[:-1]),
-                                "lastName": parts[-1],
-                                "creatorType": "author"
-                            })
+                            item["creators"].append(
+                                {
+                                    "firstName": " ".join(parts[:-1]),
+                                    "lastName": parts[-1],
+                                    "creatorType": "author",
+                                }
+                            )
                 else:
                     item["title"] = title_text
 
-            pub_elem = doc.select_one('li.ribbon-database > a > span')
+            pub_elem = doc.select_one("li.ribbon-database > a > span")
             if pub_elem:
                 item["publicationTitle"] = pub_elem.get_text(strip=True)
 
-            date_elem = doc.select_one('li.ribbon-year > a > span')
+            date_elem = doc.select_one("li.ribbon-year > a > span")
             if date_elem:
                 item["date"] = date_elem.get_text(strip=True)
 
     else:
         # Old format pages
-        title_tag = doc.select_one('head > title')
+        title_tag = doc.select_one("head > title")
         if title_tag:
             vol_iss = title_tag.get_text(strip=True)
-            match = re.search(r'^([^[]*)\[(\d+)\](.*)\(([^)]*)\)$', vol_iss)
+            match = re.search(r"^([^[]*)\[(\d+)\](.*)\(([^)]*)\)$", vol_iss)
             if match:
                 item["title"] = match.group(1).strip()
                 item["dateDecided"] = match.group(4)
                 court_number = match.group(3).strip().split()
                 if len(court_number) >= 2:
                     item["court"] = court_number[0]
-                    item["docketNumber"] = re.sub(r'[^\w]*$', '', court_number[1])
+                    item["docketNumber"] = re.sub(r"[^\w]*$", "", court_number[1])
             else:
                 item["title"] = vol_iss
 
@@ -240,8 +244,8 @@ def do_web(doc: Any, url: str) -> List[Dict[str, Any]]:
         return []
     else:
         # Handle classic.austlii.edu.au redirect
-        if 'classic.austlii.edu.au' in url:
+        if "classic.austlii.edu.au" in url:
             parsed = urlparse(url)
-            url = url.replace('classic.austlii.edu.au', 'www.austlii.edu.au')
+            url = url.replace("classic.austlii.edu.au", "www.austlii.edu.au")
 
         return [scrape(doc, url)]