scitex 2.5.0__py3-none-any.whl → 2.7.3__py3-none-any.whl

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

@@ -34,38 +34,40 @@ class BloombergTranslator:
         "inRepository": True,
         "translatorType": 4,
         "browserSupport": "gcsibv",
-        "lastUpdated": "2016-09-08 20:56:54"
+        "lastUpdated": "2016-09-08 20:56:54",
     }
 
     def detect_web(self, doc: BeautifulSoup, url: str) -> str:
         """Detect page type."""
-        if '/articles/' in url:
-            return 'newspaperArticle'
+        if "/articles/" in url:
+            return "newspaperArticle"
 
-        og_type_tag = doc.find('meta', {'property': 'og:type'})
-        if og_type_tag and og_type_tag.get('content') == 'article':
-            return 'newspaperArticle'
+        og_type_tag = doc.find("meta", {"property": "og:type"})
+        if og_type_tag and og_type_tag.get("content") == "article":
+            return "newspaperArticle"
 
-        if '/videos/' in url:
-            return 'tvBroadcast'
+        if "/videos/" in url:
+            return "tvBroadcast"
 
         if self._get_search_results(doc, check_only=True):
-            return 'multiple'
+            return "multiple"
 
-        return ''
+        return ""
 
-    def _get_search_results(self, doc: BeautifulSoup, check_only: bool = False) -> Dict[str, str]:
+    def _get_search_results(
+        self, doc: BeautifulSoup, check_only: bool = False
+    ) -> Dict[str, str]:
         """Get search results."""
         items = {}
         rows = doc.select('a[data-resource-id], a[data-tracker-label="headline"]')
 
         for row in rows:
-            href = row.get('href')
+            href = row.get("href")
             title = row.get_text(strip=True)
             if not href or not title:
                 continue
             if check_only:
-                return {'found': True}
+                return {"found": True}
             items[href] = title
 
         return items
@@ -74,9 +76,9 @@ class BloombergTranslator:
         """Extract data from the page."""
         page_type = self.detect_web(doc, url)
 
-        if page_type == 'multiple':
+        if page_type == "multiple":
             items = self._get_search_results(doc, check_only=False)
-            return [{'url': u} for u in items.keys()]
+            return [{"url": u} for u in items.keys()]
         else:
             return [self.scrape(doc, url, page_type)]
 
@@ -93,63 +95,61 @@ class BloombergTranslator:
             Dictionary containing metadata
         """
         item = {
-            'itemType': item_type if item_type else 'newspaperArticle',
-            'url': url,
-            'creators': [],
-            'tags': [],
-            'attachments': []
+            "itemType": item_type if item_type else "newspaperArticle",
+            "url": url,
+            "creators": [],
+            "tags": [],
+            "attachments": [],
         }
 
         # Extract title
-        title_tag = doc.find('meta', {'property': 'og:title'})
+        title_tag = doc.find("meta", {"property": "og:title"})
         if title_tag:
-            item['title'] = title_tag.get('content', '')
+            item["title"] = title_tag.get("content", "")
 
         # Extract authors
         author_tags = doc.select('meta[name="author"], meta[property="article:author"]')
         for author_tag in author_tags:
-            author_name = author_tag.get('content', '').strip()
+            author_name = author_tag.get("content", "").strip()
             if author_name:
-                item['creators'].append(self._clean_author(author_name, 'author'))
+                item["creators"].append(self._clean_author(author_name, "author"))
 
         # Extract date
-        date_tag = doc.find('meta', {'property': 'article:published_time'})
+        date_tag = doc.find("meta", {"property": "article:published_time"})
         if date_tag:
-            item['date'] = date_tag.get('content', '')
-        elif not item.get('date'):
+            item["date"] = date_tag.get("content", "")
+        elif not item.get("date"):
             # Try alternate source from microdata
             time_tag = doc.select_one('main time[itemprop="datePublished"]')
             if time_tag:
-                item['date'] = time_tag.get('datetime', '')
+                item["date"] = time_tag.get("datetime", "")
 
         # Extract abstract
-        abstract_tag = doc.find('meta', {'property': 'og:description'})
+        abstract_tag = doc.find("meta", {"property": "og:description"})
         if abstract_tag:
-            item['abstractNote'] = abstract_tag.get('content', '')
+            item["abstractNote"] = abstract_tag.get("content", "")
 
         # Extract publication title
-        site_name_tag = doc.find('meta', {'property': 'og:site_name'})
+        site_name_tag = doc.find("meta", {"property": "og:site_name"})
         if site_name_tag:
-            pub_title = site_name_tag.get('content', '')
-            if item_type == 'tvBroadcast':
-                item['programTitle'] = pub_title
+            pub_title = site_name_tag.get("content", "")
+            if item_type == "tvBroadcast":
+                item["programTitle"] = pub_title
             else:
-                item['publicationTitle'] = pub_title
+                item["publicationTitle"] = pub_title
 
         # Extract tags
-        keywords_tag = doc.find('meta', {'property': 'keywords'})
+        keywords_tag = doc.find("meta", {"property": "keywords"})
         if keywords_tag:
-            keywords = keywords_tag.get('content', '')
+            keywords = keywords_tag.get("content", "")
             if keywords:
-                tag_list = [k.strip() for k in keywords.split(',') if k.strip()]
-                item['tags'] = [{'tag': t} for t in tag_list]
+                tag_list = [k.strip() for k in keywords.split(",") if k.strip()]
+                item["tags"] = [{"tag": t} for t in tag_list]
 
         # Add snapshot
-        item['attachments'].append({
-            'title': 'Snapshot',
-            'mimeType': 'text/html',
-            'url': url
-        })
+        item["attachments"].append(
+            {"title": "Snapshot", "mimeType": "text/html", "url": url}
+        )
 
         return item
 
@@ -160,13 +160,9 @@ class BloombergTranslator:
 
         if len(parts) >= 2:
             return {
-                'firstName': ' '.join(parts[:-1]),
-                'lastName': parts[-1],
-                'creatorType': creator_type
+                "firstName": " ".join(parts[:-1]),
+                "lastName": parts[-1],
+                "creatorType": creator_type,
             }
         else:
-            return {
-                'lastName': name,
-                'creatorType': creator_type,
-                'fieldMode': True
-            }
+            return {"lastName": name, "creatorType": creator_type, "fieldMode": True}

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

@@ -34,7 +34,7 @@ class BloomsburyFoodLibraryTranslator:
         "inRepository": True,
         "translatorType": 4,
         "browserSupport": "gcsibv",
-        "lastUpdated": "2021-08-03 01:17:12"
+        "lastUpdated": "2021-08-03 01:17:12",
     }
 
     def detect_web(self, doc: BeautifulSoup, url: str) -> str:
@@ -42,36 +42,38 @@ class BloomsburyFoodLibraryTranslator:
         ris_link = doc.select_one('a[href*="/getris"]')
         if not ris_link:
             if self._get_search_results(doc, check_only=True):
-                return 'multiple'
-            return ''
+                return "multiple"
+            return ""
 
         # Determine type based on URL and facets
-        if 'bloomsburyfoodlibrary.com/encyclopedia-chapter' in url:
-            subfacet = doc.select_one('.subfacet')
-            if subfacet and 'Book chapter' in subfacet.get_text():
-                return 'bookSection'
+        if "bloomsburyfoodlibrary.com/encyclopedia-chapter" in url:
+            subfacet = doc.select_one(".subfacet")
+            if subfacet and "Book chapter" in subfacet.get_text():
+                return "bookSection"
             else:
-                return 'encyclopediaArticle'
-        elif 'bloomsburyfoodlibrary.com/audio' in url:
+                return "encyclopediaArticle"
+        elif "bloomsburyfoodlibrary.com/audio" in url:
             # Not well supported
-            return ''
-        elif 'bloomsburyfoodlibrary.com/museum' in url:
-            return 'artwork'
+            return ""
+        elif "bloomsburyfoodlibrary.com/museum" in url:
+            return "artwork"
         else:
-            return 'book'
+            return "book"
 
-    def _get_search_results(self, doc: BeautifulSoup, check_only: bool = False) -> Dict[str, str]:
+    def _get_search_results(
+        self, doc: BeautifulSoup, check_only: bool = False
+    ) -> Dict[str, str]:
         """Get search results."""
         items = {}
-        rows = doc.select('a#search-result-link')
+        rows = doc.select("a#search-result-link")
 
         for row in rows:
-            href = row.get('href')
+            href = row.get("href")
             title = row.get_text(strip=True)
             if not href or not title:
                 continue
             if check_only:
-                return {'found': True}
+                return {"found": True}
             items[href] = title
 
         return items
@@ -80,9 +82,9 @@ class BloomsburyFoodLibraryTranslator:
         """Extract data from the page."""
         page_type = self.detect_web(doc, url)
 
-        if page_type == 'multiple':
+        if page_type == "multiple":
             items = self._get_search_results(doc, check_only=False)
-            return [{'url': u} for u in items.keys()]
+            return [{"url": u} for u in items.keys()]
         else:
             return [self.scrape(doc, url, page_type)]
 
@@ -99,37 +101,35 @@ class BloomsburyFoodLibraryTranslator:
             Dictionary containing metadata
         """
         item = {
-            'itemType': item_type if item_type else 'book',
-            'libraryCatalog': 'Bloomsbury Food Library',
-            'url': url,
-            'creators': [],
-            'tags': [],
-            'attachments': []
+            "itemType": item_type if item_type else "book",
+            "libraryCatalog": "Bloomsbury Food Library",
+            "url": url,
+            "creators": [],
+            "tags": [],
+            "attachments": [],
         }
 
         # Get RIS URL
         ris_link = doc.select_one('a[href*="/getris"]')
         if ris_link:
-            item['_ris_url'] = ris_link.get('href')
+            item["_ris_url"] = ris_link.get("href")
 
         # Extract basic metadata from page (fallback)
-        title_tag = doc.find('meta', {'property': 'og:title'})
+        title_tag = doc.find("meta", {"property": "og:title"})
         if title_tag:
-            title = title_tag.get('content', '')
+            title = title_tag.get("content", "")
             # Clean title
-            title = title.replace(' : ', ': ')
-            item['title'] = title
+            title = title.replace(" : ", ": ")
+            item["title"] = title
 
         # Extract ISBN
-        isbn_tag = doc.find('meta', {'property': 'og:isbn'})
+        isbn_tag = doc.find("meta", {"property": "og:isbn"})
         if isbn_tag:
-            item['ISBN'] = isbn_tag.get('content', '')
+            item["ISBN"] = isbn_tag.get("content", "")
 
         # Add snapshot
-        item['attachments'].append({
-            'title': 'Snapshot',
-            'mimeType': 'text/html',
-            'url': url
-        })
+        item["attachments"].append(
+            {"title": "Snapshot", "mimeType": "text/html", "url": url}
+        )
 
         return item

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

@@ -34,19 +34,21 @@ class BlueskyTranslator:
         "inRepository": True,
         "translatorType": 4,
         "browserSupport": "gcsibv",
-        "lastUpdated": "2025-03-26 14:26:25"
+        "lastUpdated": "2025-03-26 14:26:25",
     }
 
-    HANDLE_RE = re.compile(r'(?:/profile/)(([^/]+))')
-    POST_ID_RE = re.compile(r'(?:/post/)([a-zA-Z0-9]+)')
+    HANDLE_RE = re.compile(r"(?:/profile/)(([^/]+))")
+    POST_ID_RE = re.compile(r"(?:/post/)([a-zA-Z0-9]+)")
 
     def detect_web(self, doc: BeautifulSoup, url: str) -> str:
         """Detect page type."""
-        if ('/post/' in url and
-            self.HANDLE_RE.search(url) and
-            self.POST_ID_RE.search(url)):
-            return 'forumPost'
-        return ''
+        if (
+            "/post/" in url
+            and self.HANDLE_RE.search(url)
+            and self.POST_ID_RE.search(url)
+        ):
+            return "forumPost"
+        return ""
 
     def do_web(self, doc: BeautifulSoup, url: str) -> List[Dict[str, Any]]:
         """Extract data from the page using API."""
@@ -68,25 +70,27 @@ class BlueskyTranslator:
         post_id_match = self.POST_ID_RE.search(url)
 
         if not handle_match or not post_id_match:
-            return {'error': 'Could not extract handle or post ID from URL'}
+            return {"error": "Could not extract handle or post ID from URL"}
 
         found_handle = handle_match.group(1)
         found_post_id = post_id_match.group(1)
 
         # Construct API URL
-        api_url = (f'https://public.api.bsky.app/xrpc/app.bsky.feed.getPostThread'
-                  f'?uri=at://{found_handle}/app.bsky.feed.post/{found_post_id}')
+        api_url = (
+            f"https://public.api.bsky.app/xrpc/app.bsky.feed.getPostThread"
+            f"?uri=at://{found_handle}/app.bsky.feed.post/{found_post_id}"
+        )
 
         item = {
-            'itemType': 'forumPost',
-            'forumTitle': 'Bluesky',
-            'postType': 'Post',
-            'url': url,
-            'creators': [],
-            'tags': [],
-            'notes': [],
-            'attachments': [],
-            '_api_url': api_url  # Signal that API request is needed
+            "itemType": "forumPost",
+            "forumTitle": "Bluesky",
+            "postType": "Post",
+            "url": url,
+            "creators": [],
+            "tags": [],
+            "notes": [],
+            "attachments": [],
+            "_api_url": api_url,  # Signal that API request is needed
         }
 
         # Note: In a full implementation, this would make the API request
@@ -103,11 +107,9 @@ class BlueskyTranslator:
         # - thread.replies (for reply count - adds note)
 
         # Add snapshot
-        item['attachments'].append({
-            'title': 'Snapshot',
-            'mimeType': 'text/html',
-            'url': url
-        })
+        item["attachments"].append(
+            {"title": "Snapshot", "mimeType": "text/html", "url": url}
+        )
 
         return item
 
@@ -120,8 +122,8 @@ class BlueskyTranslator:
         if word_boundary:
             # Find last space before max_length
             truncated = text[:max_length]
-            last_space = truncated.rfind(' ')
+            last_space = truncated.rfind(" ")
             if last_space > 0:
-                return truncated[:last_space] + '...'
+                return truncated[:last_space] + "..."
 
-        return text[:max_length] + '...'
+        return text[:max_length] + "..."

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

@@ -83,7 +83,7 @@ class BnFISBNTranslator(BaseTranslator):
             BnF SRU API search URL
         """
         # Clean ISBN (remove hyphens and spaces)
-        clean_isbn = re.sub(r'[-\s]', '', isbn)
+        clean_isbn = re.sub(r"[-\s]", "", isbn)
 
         # BnF SRU API query
         # Line 50: URL template with ISBN query