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

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

@@ -73,9 +73,9 @@ class IEEEXploreTranslator(BaseTranslator):
             # Method 1: Extract arnumber from current URL (JS line 135)
             # Match patterns: arnumber=123456 or /document/123456
             current_url = page.url
-            arnumber_match = re.search(r'arnumber=(\d+)', current_url)
+            arnumber_match = re.search(r"arnumber=(\d+)", current_url)
             if not arnumber_match:
-                arnumber_match = re.search(r'/document/(\d+)', current_url)
+                arnumber_match = re.search(r"/document/(\d+)", current_url)
 
             if arnumber_match:
                 arnumber = arnumber_match.group(1)
@@ -94,11 +94,13 @@ class IEEEXploreTranslator(BaseTranslator):
                     # Check for PDF link in the page (JS lines 176-177)
                     try:
                         # Look for iframe with PDF
-                        iframe_src = await page.locator('iframe[src*=".pdf"], iframe[src*="/getPDF.jsp"]').first.get_attribute('src', timeout=2000)
+                        iframe_src = await page.locator(
+                            'iframe[src*=".pdf"], iframe[src*="/getPDF.jsp"]'
+                        ).first.get_attribute("src", timeout=2000)
                         if iframe_src:
-                            if iframe_src.startswith('/'):
+                            if iframe_src.startswith("/"):
                                 pdf_url = f"https://ieeexplore.ieee.org{iframe_src}"
-                            elif not iframe_src.startswith('http'):
+                            elif not iframe_src.startswith("http"):
                                 pdf_url = f"https://ieeexplore.ieee.org/{iframe_src}"
                             else:
                                 pdf_url = iframe_src
@@ -125,12 +127,14 @@ class IEEEXploreTranslator(BaseTranslator):
         # Method 2: Look for PDF download link on the page
         try:
             # Check for direct PDF download links
-            pdf_link = await page.locator('a[href*=".pdf"], a[href*="/getPDF.jsp"], a[href*="/stamp/"]').first.get_attribute('href', timeout=2000)
+            pdf_link = await page.locator(
+                'a[href*=".pdf"], a[href*="/getPDF.jsp"], a[href*="/stamp/"]'
+            ).first.get_attribute("href", timeout=2000)
             if pdf_link:
                 # Make absolute URL if needed
-                if pdf_link.startswith('/'):
+                if pdf_link.startswith("/"):
                     pdf_link = f"https://ieeexplore.ieee.org{pdf_link}"
-                elif not pdf_link.startswith('http'):
+                elif not pdf_link.startswith("http"):
                     pdf_link = f"https://ieeexplore.ieee.org/{pdf_link}"
                 pdf_urls.append(pdf_link)
                 return pdf_urls
@@ -143,7 +147,7 @@ class IEEEXploreTranslator(BaseTranslator):
             script_elements = await page.locator('script[type="text/javascript"]').all()
             for script_element in script_elements:
                 script = await script_element.text_content()
-                if script and 'global.document.metadata' in script:
+                if script and "global.document.metadata" in script:
                     # Try to extract arnumber from metadata
                     arnumber_match = re.search(r'"arnumber"\s*:\s*"(\d+)"', script)
                     if not arnumber_match:
@@ -187,50 +191,50 @@ class IEEEXploreTranslator(BaseTranslator):
         try:
             # Extract arnumber from URL (JS line 135)
             current_url = page.url
-            arnumber_match = re.search(r'arnumber=(\d+)', current_url)
+            arnumber_match = re.search(r"arnumber=(\d+)", current_url)
             if not arnumber_match:
-                arnumber_match = re.search(r'/document/(\d+)', current_url)
+                arnumber_match = re.search(r"/document/(\d+)", current_url)
 
             if not arnumber_match:
                 return None
 
             arnumber = arnumber_match.group(1)
-            metadata['arnumber'] = arnumber
+            metadata["arnumber"] = arnumber
 
             # Extract metadata from script tag (JS lines 138-149)
             script_elements = await page.locator('script[type="text/javascript"]').all()
             for script_element in script_elements:
                 script = await script_element.text_content()
-                if script and 'global.document.metadata' in script:
+                if script and "global.document.metadata" in script:
                     try:
                         # Extract JSON metadata (JS lines 140-148)
                         data_raw = script.split("global.document.metadata")[1]
-                        data_raw = re.sub(r'^=', '', data_raw)
-                        data_raw = re.sub(r'};[\s\S]*$', '}', data_raw)
+                        data_raw = re.sub(r"^=", "", data_raw)
+                        data_raw = re.sub(r"};[\s\S]*$", "}", data_raw)
                         data = json.loads(data_raw)
 
                         # Extract authors (JS lines 220-229)
-                        if 'authors' in data and data['authors']:
+                        if "authors" in data and data["authors"]:
                             authors = []
-                            for author in data['authors']:
+                            for author in data["authors"]:
                                 author_name = {
-                                    'firstName': author.get('firstName', ''),
-                                    'lastName': author.get('lastName', '')
+                                    "firstName": author.get("firstName", ""),
+                                    "lastName": author.get("lastName", ""),
                                 }
                                 authors.append(author_name)
-                            metadata['authors'] = authors
+                            metadata["authors"] = authors
 
                         # Extract other metadata
-                        if 'title' in data:
-                            metadata['title'] = data['title']
-                        if 'doi' in data:
-                            metadata['doi'] = data['doi']
-                        if 'abstract' in data:
-                            metadata['abstract'] = data['abstract']
-                        if 'publicationTitle' in data:
-                            metadata['publicationTitle'] = data['publicationTitle']
-                        if 'issn' in data:
-                            metadata['issn'] = data.get('issn', [])
+                        if "title" in data:
+                            metadata["title"] = data["title"]
+                        if "doi" in data:
+                            metadata["doi"] = data["doi"]
+                        if "abstract" in data:
+                            metadata["abstract"] = data["abstract"]
+                        if "publicationTitle" in data:
+                            metadata["publicationTitle"] = data["publicationTitle"]
+                        if "issn" in data:
+                            metadata["issn"] = data.get("issn", [])
 
                         break
                     except Exception:
@@ -239,16 +243,18 @@ class IEEEXploreTranslator(BaseTranslator):
             # Determine item type (JS lines 44-50)
             # Check breadcrumbs for "Conferences"
             try:
-                first_breadcrumb = await page.locator('div[class*="breadcrumbs"] a').first.text_content(timeout=2000)
+                first_breadcrumb = await page.locator(
+                    'div[class*="breadcrumbs"] a'
+                ).first.text_content(timeout=2000)
                 if first_breadcrumb and "Conference" in first_breadcrumb:
-                    metadata['itemType'] = 'conferencePaper'
+                    metadata["itemType"] = "conferencePaper"
                 else:
-                    metadata['itemType'] = 'journalArticle'
+                    metadata["itemType"] = "journalArticle"
             except Exception:
-                metadata['itemType'] = 'journalArticle'
+                metadata["itemType"] = "journalArticle"
 
             # Clean URL (JS lines 237-239)
-            metadata['url'] = re.sub(r'[?#].*', '', current_url)
+            metadata["url"] = re.sub(r"[?#].*", "", current_url)
 
             return metadata
 

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

@@ -85,7 +85,9 @@ if __name__ == "__main__":
         test_url = "http://www.int-res.com/abstracts/meps/v403/p13-27/"
 
         print(f"Testing InterResearchScienceCenterTranslator with URL: {test_url}")
-        print(f"URL matches pattern: {InterResearchScienceCenterTranslator.matches_url(test_url)}\n")
+        print(
+            f"URL matches pattern: {InterResearchScienceCenterTranslator.matches_url(test_url)}\n"
+        )
 
         async with async_playwright() as p:
             browser = await p.chromium.launch(headless=True)
@@ -97,7 +99,9 @@ if __name__ == "__main__":
             await page.wait_for_load_state("domcontentloaded")
 
             print("Extracting PDF URLs...")
-            pdf_urls = await InterResearchScienceCenterTranslator.extract_pdf_urls_async(page)
+            pdf_urls = (
+                await InterResearchScienceCenterTranslator.extract_pdf_urls_async(page)
+            )
 
             print(f"\nResults:")
             print(f"  Found {len(pdf_urls)} PDF URL(s)")

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

@@ -12,7 +12,9 @@ class JiscHistoricalTextsTranslator(BaseTranslator):
     """JISC Historical Texts."""
 
     LABEL = "JISC Historical Texts"
-    URL_TARGET_PATTERN = r"^https?://(data\.)?[^/]*historicaltexts\.jisc\.ac\.uk/(view|results)\?"
+    URL_TARGET_PATTERN = (
+        r"^https?://(data\.)?[^/]*historicaltexts\.jisc\.ac\.uk/(view|results)\?"
+    )
 
     @classmethod
     def matches_url(cls, url: str) -> bool:

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

@@ -83,12 +83,12 @@ class JSTORTranslator(BaseTranslator):
         jid = urllib.parse.unquote(match.group(1))
 
         # Remove .pdf extension if present
-        if jid.lower().endswith('.pdf'):
+        if jid.lower().endswith(".pdf"):
             jid = jid[:-4]
 
         # If not already a DOI (starting with 10.), convert to JSTOR DOI
-        if not jid.startswith('10.'):
-            jid = f'10.2307/{jid}'
+        if not jid.startswith("10."):
+            jid = f"10.2307/{jid}"
 
         return jid
 
@@ -104,21 +104,21 @@ class JSTORTranslator(BaseTranslator):
         """
         try:
             # Check for book indicators
-            book_button = await page.query_selector('.book_info_button')
+            book_button = await page.query_selector(".book_info_button")
             if book_button:
-                return 'book'
+                return "book"
 
             # Check for book chapter indicators
-            analytics = await page.query_selector('script[data-analytics-provider]')
+            analytics = await page.query_selector("script[data-analytics-provider]")
             if analytics:
                 content = await analytics.inner_text()
-                if 'chapter view' in content:
-                    return 'bookSection'
+                if "chapter view" in content:
+                    return "bookSection"
         except Exception:
             pass
 
         # Default to journal article
-        return 'journalArticle'
+        return "journalArticle"
 
     @classmethod
     async def _check_pdf_access(cls, page: Page) -> bool:
@@ -142,7 +142,7 @@ class JSTORTranslator(BaseTranslator):
                 'a[href*="pdfplus"]',
                 'a[href*=".pdf"]',
                 'button:has-text("Download PDF")',
-                '.download-pdf'
+                ".download-pdf",
             ]
 
             for selector in pdf_selectors:
@@ -187,7 +187,7 @@ class JSTORTranslator(BaseTranslator):
             item_type = await cls._detect_item_type(page)
 
             # Books don't have PDFs
-            if item_type == 'book':
+            if item_type == "book":
                 return pdf_urls
 
             # Check if PDF access is available
@@ -196,7 +196,9 @@ class JSTORTranslator(BaseTranslator):
             if has_access:
                 # Construct PDF URL
                 # JSTOR uses pdfplus for enhanced PDFs
-                pdf_url = f"https://www.jstor.org/stable/pdfplus/{jid}.pdf?acceptTC=true"
+                pdf_url = (
+                    f"https://www.jstor.org/stable/pdfplus/{jid}.pdf?acceptTC=true"
+                )
                 pdf_urls.append(pdf_url)
 
         except Exception as e:

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

@@ -12,7 +12,9 @@ class KoreanNationalLibraryTranslator(BaseTranslator):
     """Korean National Library."""
 
     LABEL = "Korean National Library"
-    URL_TARGET_PATTERN = r"^https?://www\.nl\.go\.kr/(EN|NL)/contents/(eng)?[sS]earch\.do"
+    URL_TARGET_PATTERN = (
+        r"^https?://www\.nl\.go\.kr/(EN|NL)/contents/(eng)?[sS]earch\.do"
+    )
 
     @classmethod
     def matches_url(cls, url: str) -> bool:

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

@@ -12,7 +12,9 @@ class LaTimesTranslator(BaseTranslator):
     """LA Times."""
 
     LABEL = "LA Times"
-    URL_TARGET_PATTERN = r"^https?://(www\.|travel\.|articles\.|latimesblogs\.)?latimes\.com"
+    URL_TARGET_PATTERN = (
+        r"^https?://(www\.|travel\.|articles\.|latimesblogs\.)?latimes\.com"
+    )
 
     @classmethod
     def matches_url(cls, url: str) -> bool:

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

@@ -12,7 +12,9 @@ class LandesbibliographieBadenWurttembergTranslator(BaseTranslator):
     """Landesbibliographie Baden-Wurttemberg."""
 
     LABEL = "Landesbibliographie Baden-Wurttemberg"
-    URL_TARGET_PATTERN = r"^https?://(www\.)?(statistik\.baden-wuerttemberg|statistik-bw)\.de/LABI"
+    URL_TARGET_PATTERN = (
+        r"^https?://(www\.)?(statistik\.baden-wuerttemberg|statistik-bw)\.de/LABI"
+    )
 
     @classmethod
     def matches_url(cls, url: str) -> bool:

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

@@ -12,7 +12,9 @@ class LegislativeInsightTranslator(BaseTranslator):
     """Legislative Insight."""
 
     LABEL = "Legislative Insight"
-    URL_TARGET_PATTERN = r"^https?://(preprod\.)?li\.proquest\.com/legislativeinsight/LegHistMain\.jsp"
+    URL_TARGET_PATTERN = (
+        r"^https?://(preprod\.)?li\.proquest\.com/legislativeinsight/LegHistMain\.jsp"
+    )
 
     @classmethod
     def matches_url(cls, url: str) -> bool:

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

@@ -12,7 +12,9 @@ class LibrariesTasmaniaTranslator(BaseTranslator):
     """Libraries Tasmania."""
 
     LABEL = "Libraries Tasmania"
-    URL_TARGET_PATTERN = r"^https?://librariestas\.ent\.sirsidynix\.net\.au/client/en_AU/"
+    URL_TARGET_PATTERN = (
+        r"^https?://librariestas\.ent\.sirsidynix\.net\.au/client/en_AU/"
+    )
 
     @classmethod
     def matches_url(cls, url: str) -> bool:

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

@@ -12,7 +12,9 @@ class LibraryCatalogKohaTranslator(BaseTranslator):
     """Library Catalog (Koha)."""
 
     LABEL = "Library Catalog (Koha)"
-    URL_TARGET_PATTERN = r"^https?://[^/]+/cgi-bin/koha/opac-(detail|search|shelves)\.pl\?"
+    URL_TARGET_PATTERN = (
+        r"^https?://[^/]+/cgi-bin/koha/opac-(detail|search|shelves)\.pl\?"
+    )
 
     @classmethod
     def matches_url(cls, url: str) -> bool:

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

@@ -18,7 +18,7 @@ from typing import List
 from playwright.async_api import Page, Error as PlaywrightError
 
 # Explicit public API - only export the translator class
-__all__ = ['LingBuzzTranslator']
+__all__ = ["LingBuzzTranslator"]
 
 # Private module-level logger - not exported
 _logger = logging.getLogger(__name__)
@@ -125,7 +125,7 @@ class LingBuzzTranslator:
             # Validate and filter URLs
             if urls and isinstance(urls, list):
                 for url in urls:
-                    if url and isinstance(url, str) and url.startswith('http'):
+                    if url and isinstance(url, str) and url.startswith("http"):
                         pdf_urls.append(url)
                     else:
                         _logger.warning(f"LingBuzz: Invalid URL format: {url}")

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

@@ -8,7 +8,9 @@ from playwright.async_api import Page
 from ..core.base import BaseTranslator
 
 
-class MaxPlanckInstituteForTheHistoryOfScienceVirtualLaboratoryLibraryTranslator(BaseTranslator):
+class MaxPlanckInstituteForTheHistoryOfScienceVirtualLaboratoryLibraryTranslator(
+    BaseTranslator
+):
     """Max Planck Institute for the History of Science Virtual Laboratory Library."""
 
     LABEL = "Max Planck Institute for the History of Science Virtual Laboratory Library"

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

@@ -29,7 +29,9 @@ class MDPITranslator(BaseTranslator):
 
         # Method 1: citation_pdf_url meta tag (primary method for MDPI)
         try:
-            pdf_url = await page.locator('meta[name="citation_pdf_url"]').first.get_attribute('content', timeout=2000)
+            pdf_url = await page.locator(
+                'meta[name="citation_pdf_url"]'
+            ).first.get_attribute("content", timeout=2000)
             if pdf_url:
                 pdf_urls.append(pdf_url)
                 return pdf_urls
@@ -39,11 +41,13 @@ class MDPITranslator(BaseTranslator):
         # Method 2: Direct PDF download link
         try:
             # MDPI typically has a download link with specific class
-            pdf_link = await page.locator('a.download[href*="/pdf"]').first.get_attribute('href', timeout=2000)
+            pdf_link = await page.locator(
+                'a.download[href*="/pdf"]'
+            ).first.get_attribute("href", timeout=2000)
             if pdf_link:
                 # Make absolute URL if needed
-                if pdf_link.startswith('/'):
-                    base_url = await page.evaluate('window.location.origin')
+                if pdf_link.startswith("/"):
+                    base_url = await page.evaluate("window.location.origin")
                     pdf_link = f"{base_url}{pdf_link}"
                 pdf_urls.append(pdf_link)
                 return pdf_urls
@@ -53,8 +57,10 @@ class MDPITranslator(BaseTranslator):
         # Method 3: Construct PDF URL from article URL
         # MDPI pattern: https://www.mdpi.com/2076-3425/9/7/156 -> https://www.mdpi.com/2076-3425/9/7/156/pdf
         try:
-            current_url = await page.evaluate('window.location.href')
-            if '/article/' not in current_url:  # Not an article page with /article/ prefix
+            current_url = await page.evaluate("window.location.href")
+            if (
+                "/article/" not in current_url
+            ):  # Not an article page with /article/ prefix
                 # Try appending /pdf to current URL
                 pdf_url = f"{current_url.rstrip('/')}/pdf"
                 pdf_urls.append(pdf_url)

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

@@ -12,7 +12,9 @@ class MicrobiologySocietyJournalsTranslator(BaseTranslator):
     """Microbiology Society Journals."""
 
     LABEL = "Microbiology Society Journals"
-    URL_TARGET_PATTERN = r"^https?://(www\.)?(\w)+\.microbiologyresearch\.org/(content/journal/|search?)"
+    URL_TARGET_PATTERN = (
+        r"^https?://(www\.)?(\w)+\.microbiologyresearch\.org/(content/journal/|search?)"
+    )
 
     @classmethod
     def matches_url(cls, url: str) -> bool:

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

@@ -12,7 +12,9 @@ class MidasJournalsTranslator(BaseTranslator):
     """MIDAS Journals."""
 
     LABEL = "MIDAS Journals"
-    URL_TARGET_PATTERN = r"^https?://(www\.)?(insight-journal|midasjournal|vtkjournal)\.org/"
+    URL_TARGET_PATTERN = (
+        r"^https?://(www\.)?(insight-journal|midasjournal|vtkjournal)\.org/"
+    )
 
     @classmethod
     def matches_url(cls, url: str) -> bool:

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

@@ -12,7 +12,9 @@ class NagoyaUniversityOpacTranslator(BaseTranslator):
     """Nagoya University OPAC."""
 
     LABEL = "Nagoya University OPAC"
-    URL_TARGET_PATTERN = r"^https?://opac\.nul\.nagoya-u\.ac\.jp/webopac/(catdbl\.do|ctlsrh\.do)"
+    URL_TARGET_PATTERN = (
+        r"^https?://opac\.nul\.nagoya-u\.ac\.jp/webopac/(catdbl\.do|ctlsrh\.do)"
+    )
 
     @classmethod
     def matches_url(cls, url: str) -> bool:

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

@@ -48,7 +48,7 @@ class NaturePublishingGroupTranslator(BaseTranslator):
             True if URL matches Nature Publishing Group pattern
         """
         # Exclude PDF files (JS line 477)
-        if url.endswith('.pdf'):
+        if url.endswith(".pdf"):
             return False
 
         # Basic nature.com check
@@ -57,16 +57,26 @@ class NaturePublishingGroupTranslator(BaseTranslator):
 
         # More specific checks based on JavaScript detectWeb (lines 478-500)
         # Single article patterns (JS line 478)
-        if re.search(r'/(full|abs)/[^/]+($|\?|#)|/fp/.+?[?&]lang=ja(?:&|$)|/articles/', url):
+        if re.search(
+            r"/(full|abs)/[^/]+($|\?|#)|/fp/.+?[?&]lang=ja(?:&|$)|/articles/", url
+        ):
             return True
 
         # Multiple items patterns (JS lines 481-489)
-        if ('/research/' in url or '/topten/' in url or '/most.htm' in url or
-            '/search?' in url or 'sp-q=' in url or '/archive/' in url):
+        if (
+            "/research/" in url
+            or "/topten/" in url
+            or "/most.htm" in url
+            or "/search?" in url
+            or "sp-q=" in url
+            or "/archive/" in url
+        ):
             return True
 
         # Issue table of contents patterns
-        if re.search(r'journal/v\d+/n\d+/', url) or re.search(r'volumes/\d+/issues/\d+', url):
+        if re.search(r"journal/v\d+/n\d+/", url) or re.search(
+            r"volumes/\d+/issues/\d+", url
+        ):
             return True
 
         return False
@@ -102,8 +112,7 @@ class NaturePublishingGroupTranslator(BaseTranslator):
 
             # Pattern: https://www.nature.com/.../full/article_id.html -> .../pdf/article_id.pdf
             url_match = re.match(
-                r'(^[^#?]+/)(?:full|abs)(\/[^#?]+?\.)[a-zA-Z]+(?=$|\?|#)',
-                current_url
+                r"(^[^#?]+/)(?:full|abs)(\/[^#?]+?\.)[a-zA-Z]+(?=$|\?|#)", current_url
             )
 
             if url_match:
@@ -118,18 +127,20 @@ class NaturePublishingGroupTranslator(BaseTranslator):
         # Method 2: Look for download PDF link (JS line 273)
         # JS: return attr(doc, 'a[data-track-action="download pdf"]', 'href');
         try:
-            pdf_link = await page.locator('a[data-track-action="download pdf"]').first.get_attribute('href', timeout=2000)
+            pdf_link = await page.locator(
+                'a[data-track-action="download pdf"]'
+            ).first.get_attribute("href", timeout=2000)
             if pdf_link:
                 # Make absolute URL if needed
-                if pdf_link.startswith('/'):
-                    base_url = await page.evaluate('window.location.origin')
+                if pdf_link.startswith("/"):
+                    base_url = await page.evaluate("window.location.origin")
                     pdf_link = f"{base_url}{pdf_link}"
-                elif not pdf_link.startswith('http'):
+                elif not pdf_link.startswith("http"):
                     current_url = page.url
                     # Remove query params and fragments
-                    base_url = re.sub(r'[?#].*$', '', current_url)
+                    base_url = re.sub(r"[?#].*$", "", current_url)
                     # Remove trailing path
-                    base_url = re.sub(r'/[^/]*$', '', base_url)
+                    base_url = re.sub(r"/[^/]*$", "", base_url)
                     pdf_link = f"{base_url}/{pdf_link}"
                 return [pdf_link]
         except Exception:
@@ -139,13 +150,13 @@ class NaturePublishingGroupTranslator(BaseTranslator):
         # e.g., https://www.nature.com/articles/onc2011282
         try:
             current_url = page.url
-            if '/articles/' in current_url:
+            if "/articles/" in current_url:
                 # Extract article ID
-                article_match = re.search(r'/articles/([^/?#]+)', current_url)
+                article_match = re.search(r"/articles/([^/?#]+)", current_url)
                 if article_match:
                     article_id = article_match.group(1)
                     # Try different PDF URL patterns
-                    base_url = await page.evaluate('window.location.origin')
+                    base_url = await page.evaluate("window.location.origin")
 
                     # Pattern 1: /articles/article_id.pdf
                     pdf_url = f"{base_url}/articles/{article_id}.pdf"
@@ -155,9 +166,9 @@ class NaturePublishingGroupTranslator(BaseTranslator):
                     if pdf_links:
                         for link in pdf_links[:3]:  # Check first 3 PDF links
                             try:
-                                href = await link.get_attribute('href', timeout=1000)
+                                href = await link.get_attribute("href", timeout=1000)
                                 if href and article_id in href:
-                                    if href.startswith('/'):
+                                    if href.startswith("/"):
                                         href = f"{base_url}{href}"
                                     return [href]
                             except Exception:
@@ -171,7 +182,9 @@ class NaturePublishingGroupTranslator(BaseTranslator):
         # Method 4: Meta tag fallback
         try:
             # Some Nature pages have PDF URL in meta tags
-            pdf_url = await page.locator('meta[name="citation_pdf_url"]').first.get_attribute('content', timeout=2000)
+            pdf_url = await page.locator(
+                'meta[name="citation_pdf_url"]'
+            ).first.get_attribute("content", timeout=2000)
             if pdf_url:
                 return [pdf_url]
         except Exception:

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

@@ -12,7 +12,9 @@ class NtsbAccidentReportsTranslator(BaseTranslator):
     """NTSB Accident Reports."""
 
     LABEL = "NTSB Accident Reports"
-    URL_TARGET_PATTERN = r"^https?://(www\.)?ntsb\.gov/investigations/AccidentReports/Pages/"
+    URL_TARGET_PATTERN = (
+        r"^https?://(www\.)?ntsb\.gov/investigations/AccidentReports/Pages/"
+    )
 
     @classmethod
     def matches_url(cls, url: str) -> bool:

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

@@ -18,7 +18,7 @@ from typing import List
 from playwright.async_api import Page, Error as PlaywrightError
 
 # Explicit public API - only export the translator class
-__all__ = ['OpenEditionJournalsTranslator']
+__all__ = ["OpenEditionJournalsTranslator"]
 
 # Private module-level logger - not exported
 _logger = logging.getLogger(__name__)
@@ -102,7 +102,7 @@ class OpenEditionJournalsTranslator:
             # Validate and filter URLs
             if urls and isinstance(urls, list):
                 for url in urls:
-                    if url and isinstance(url, str) and url.startswith('http'):
+                    if url and isinstance(url, str) and url.startswith("http"):
                         pdf_urls.append(url)
                     else:
                         _logger.warning(f"OpenEdition: Invalid URL format: {url}")
@@ -130,7 +130,9 @@ if __name__ == "__main__":
 
         for test_url in test_urls:
             print(f"\nTesting OpenEditionJournalsTranslator with URL: {test_url}")
-            print(f"URL matches pattern: {OpenEditionJournalsTranslator.matches_url(test_url)}")
+            print(
+                f"URL matches pattern: {OpenEditionJournalsTranslator.matches_url(test_url)}"
+            )
 
             async with async_playwright() as p:
                 browser = await p.chromium.launch(headless=True)
@@ -142,7 +144,9 @@ if __name__ == "__main__":
                 await page.wait_for_load_state("domcontentloaded")
 
                 print("Extracting PDF URLs...")
-                pdf_urls = await OpenEditionJournalsTranslator.extract_pdf_urls_async(page)
+                pdf_urls = await OpenEditionJournalsTranslator.extract_pdf_urls_async(
+                    page
+                )
 
                 print(f"\nResults:")
                 print(f"  Found {len(pdf_urls)} PDF URL(s)")