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

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

@@ -34,12 +34,12 @@ class CurrentAffairsTranslator:
         "inRepository": True,
         "translatorType": 4,
         "browserSupport": "gcsibv",
-        "lastUpdated": "2021-08-07 00:42:35"
+        "lastUpdated": "2021-08-07 00:42:35",
     }
 
     def detect_web(self, doc: BeautifulSoup, url: str) -> str:
         """Detect if the page is a magazine article."""
-        if doc.select_one('h1.title') and doc.select_one('.primary'):
+        if doc.select_one("h1.title") and doc.select_one(".primary"):
             return "magazineArticle"
         return ""
 
@@ -52,50 +52,48 @@ class CurrentAffairsTranslator:
     def scrape(self, doc: BeautifulSoup, url: str) -> Dict[str, Any]:
         """Scrape article data from the document."""
         item = {
-            'itemType': 'magazineArticle',
-            'publicationTitle': 'Current Affairs',
-            'language': 'en',
-            'ISSN': '2471-2647',
-            'url': re.sub(r'[#?].*$', '', url),  # Remove query params and anchors
-            'creators': [],
-            'tags': [],
-            'attachments': []
+            "itemType": "magazineArticle",
+            "publicationTitle": "Current Affairs",
+            "language": "en",
+            "ISSN": "2471-2647",
+            "url": re.sub(r"[#?].*$", "", url),  # Remove query params and anchors
+            "creators": [],
+            "tags": [],
+            "attachments": [],
         }
 
         # Extract title
-        title_elem = doc.select_one('h1.title')
+        title_elem = doc.select_one("h1.title")
         if title_elem:
-            item['title'] = title_elem.get_text(strip=True)
+            item["title"] = title_elem.get_text(strip=True)
 
         # Extract abstract from meta description
-        description_meta = doc.find('meta', {'name': 'description'})
-        if description_meta and description_meta.get('content'):
-            item['abstractNote'] = description_meta['content']
+        description_meta = doc.find("meta", {"name": "description"})
+        if description_meta and description_meta.get("content"):
+            item["abstractNote"] = description_meta["content"]
 
         # Extract issue
-        issue_input = doc.select_one('#wpIssueName')
-        if issue_input and issue_input.get('value'):
-            item['issue'] = issue_input['value']
+        issue_input = doc.select_one("#wpIssueName")
+        if issue_input and issue_input.get("value"):
+            item["issue"] = issue_input["value"]
 
         # Extract date from dateline
-        dateline_elem = doc.select_one('.dateline span')
+        dateline_elem = doc.select_one(".dateline span")
         if dateline_elem:
             date_text = dateline_elem.get_text(strip=True)
             # Convert to ISO format if possible
-            item['date'] = date_text
+            item["date"] = date_text
 
         # Extract authors from bylines
-        for byline in doc.select('.primary .bylines li'):
+        for byline in doc.select(".primary .bylines li"):
             author_name = byline.get_text(strip=True)
             if author_name:
-                item['creators'].append(self._clean_author(author_name, 'author'))
+                item["creators"].append(self._clean_author(author_name, "author"))
 
         # Add snapshot attachment
-        item['attachments'].append({
-            'title': 'Snapshot',
-            'mimeType': 'text/html',
-            'url': url
-        })
+        item["attachments"].append(
+            {"title": "Snapshot", "mimeType": "text/html", "url": url}
+        )
 
         return item
 
@@ -106,13 +104,9 @@ class CurrentAffairsTranslator:
 
         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/dabi.py

@@ -34,7 +34,7 @@ class DABITranslator:
         "inRepository": True,
         "translatorType": 4,
         "browserSupport": "gcsibv",
-        "lastUpdated": "2021-09-10 18:58:10"
+        "lastUpdated": "2021-09-10 18:58:10",
     }
 
     def detect_web(self, doc: BeautifulSoup, url: str) -> str:
@@ -42,27 +42,29 @@ class DABITranslator:
         if "/vollanzeige.pl?" in url:
             return "journalArticle"
         elif "/suche.pl?" in url and self._get_search_results(doc, True):
-            return 'multiple'
+            return "multiple"
         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 from the page."""
         items = {}
         found = False
-        rows = doc.find_all('tr')[1:]  # Skip header row
+        rows = doc.find_all("tr")[1:]  # Skip header row
 
         for row in rows:
-            tds = row.find_all('td')
+            tds = row.find_all("td")
             if len(tds) < 3:
                 continue
 
-            link = tds[0].find('a')
+            link = tds[0].find("a")
             if not link:
                 continue
 
-            url = link.get('href')
+            url = link.get("href")
             author = tds[1].get_text(strip=True)
-            title = tds[2].get_text(strip=True).replace('<br>', '. ')
+            title = tds[2].get_text(strip=True).replace("<br>", ". ")
 
             if author:
                 item_text = f"{title} ({re.sub(r';.*', ' et al.', author)})"
@@ -88,114 +90,116 @@ class DABITranslator:
     def scrape(self, doc: BeautifulSoup, url: str) -> Dict[str, Any]:
         """Scrape article data from the document."""
         item = {
-            'itemType': 'journalArticle',
-            'creators': [],
-            'tags': [],
-            'attachments': []
+            "itemType": "journalArticle",
+            "creators": [],
+            "tags": [],
+            "attachments": [],
         }
 
         # Parse table rows for metadata
         data = {}
-        rows = doc.find_all('tr')
+        rows = doc.find_all("tr")
 
         for row in rows:
-            headers = row.find_all('th')
-            contents = row.find_all('td')
+            headers = row.find_all("th")
+            contents = row.find_all("td")
 
             if headers and contents:
-                header = headers[0].get_text(strip=True).replace(' ', '')
+                header = headers[0].get_text(strip=True).replace(" ", "")
                 content_html = str(contents[0])
                 data[header] = content_html.strip()
 
         # Set URL to fulltext resource if present
-        if 'URL' in data:
-            url_match = re.search(r'<a.*?href="(.*?)"', data['URL'])
+        if "URL" in data:
+            url_match = re.search(r'<a.*?href="(.*?)"', data["URL"])
             if url_match:
                 url_value = url_match.group(1)
 
-                if re.search(r'\.pdf(#.*)?$', url_value):
-                    item['attachments'].append({
-                        'url': url_value,
-                        'title': 'DABI Full Text PDF',
-                        'mimeType': 'application/pdf'
-                    })
+                if re.search(r"\.pdf(#.*)?$", url_value):
+                    item["attachments"].append(
+                        {
+                            "url": url_value,
+                            "title": "DABI Full Text PDF",
+                            "mimeType": "application/pdf",
+                        }
+                    )
                 else:
-                    item['url'] = url_value
+                    item["url"] = url_value
 
         # Handle title fields
-        if 'Titel' not in data and 'Untertitel' in data:
-            data['Titel'] = data['Untertitel']
-            del data['Untertitel']
+        if "Titel" not in data and "Untertitel" in data:
+            data["Titel"] = data["Untertitel"]
+            del data["Untertitel"]
 
-        if 'Titel' in data:
-            item['title'] = data['Titel'].replace('*', '')
+        if "Titel" in data:
+            item["title"] = data["Titel"].replace("*", "")
 
-            if 'Untertitel' in data:
-                subtitle = data['Untertitel']
-                if re.search(r'(\?|!|\.)\W?$', item['title']):
-                    item['title'] += " " + subtitle
+            if "Untertitel" in data:
+                subtitle = data["Untertitel"]
+                if re.search(r"(\?|!|\.)\W?$", item["title"]):
+                    item["title"] += " " + subtitle
                 else:
-                    item['title'] += ": " + subtitle
+                    item["title"] += ": " + subtitle
 
         # Parse authors
-        if 'Autoren' in data:
-            authors = data['Autoren'].split('; ')
+        if "Autoren" in data:
+            authors = data["Autoren"].split("; ")
             for author in authors:
-                item['creators'].append(self._clean_author(author, "author"))
+                item["creators"].append(self._clean_author(author, "author"))
 
         # Parse pages
-        if 'Anfangsseite' in data and int(data.get('Anfangsseite', 0)) > 0:
-            start_page = data['Anfangsseite']
-            end_page = data.get('Endseite', '')
+        if "Anfangsseite" in data and int(data.get("Anfangsseite", 0)) > 0:
+            start_page = data["Anfangsseite"]
+            end_page = data.get("Endseite", "")
             if end_page and int(end_page) > int(start_page):
-                item['pages'] = f"{start_page}-{end_page}"
+                item["pages"] = f"{start_page}-{end_page}"
             else:
-                item['pages'] = start_page
+                item["pages"] = start_page
 
         # Parse tags
-        if 'Schlagwörter' in data:
-            tags = data['Schlagwörter'].split('; ')
-            item['tags'] = [{'tag': tag} for tag in tags if tag]
+        if "Schlagwörter" in data:
+            tags = data["Schlagwörter"].split("; ")
+            item["tags"] = [{"tag": tag} for tag in tags if tag]
 
         # Clean publication title
-        if 'Zeitschrift' in data:
-            item['publicationTitle'] = data['Zeitschrift'].replace(' : ', ': ')
+        if "Zeitschrift" in data:
+            item["publicationTitle"] = data["Zeitschrift"].replace(" : ", ": ")
 
         # Other fields
-        if 'Jahr' in data:
-            item['date'] = data['Jahr']
-        if 'Heft' in data:
-            item['issue'] = data['Heft']
-        if 'Band' in data:
-            item['volume'] = data['Band']
-        if 'Abstract' in data:
-            item['abstractNote'] = data['Abstract']
+        if "Jahr" in data:
+            item["date"] = data["Jahr"]
+        if "Heft" in data:
+            item["issue"] = data["Heft"]
+        if "Band" in data:
+            item["volume"] = data["Band"]
+        if "Abstract" in data:
+            item["abstractNote"] = data["Abstract"]
 
         return item
 
     def _clean_author(self, name: str, creator_type: str) -> Dict[str, Any]:
         """Parse author name into first and last name."""
         name = name.strip()
-        parts = name.split(',')
+        parts = name.split(",")
 
         if len(parts) >= 2:
             # Format: "Last, First"
             return {
-                'firstName': parts[1].strip(),
-                'lastName': parts[0].strip(),
-                'creatorType': creator_type
+                "firstName": parts[1].strip(),
+                "lastName": parts[0].strip(),
+                "creatorType": creator_type,
             }
         else:
             parts = name.split()
             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
+                    "lastName": name,
+                    "creatorType": creator_type,
+                    "fieldMode": True,
                 }

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

@@ -12,7 +12,9 @@ class DagensNyheterTranslator(BaseTranslator):
     """Dagens Nyheter."""
 
     LABEL = "Dagens Nyheter"
-    URL_TARGET_PATTERN = r"^https?://www\.dn\.se/(nyheter|ekonomi|kultur-noje|sport|sok)/"
+    URL_TARGET_PATTERN = (
+        r"^https?://www\.dn\.se/(nyheter|ekonomi|kultur-noje|sport|sok)/"
+    )
 
     @classmethod
     def matches_url(cls, url: str) -> bool:

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

@@ -30,7 +30,7 @@ class DagstuhlTranslator:
         "priority": 100,
         "inRepository": True,
         "translatorType": 4,  # Web
-        "lastUpdated": "2024-11-30 08:38:44"
+        "lastUpdated": "2024-11-30 08:38:44",
     }
 
     def detect_web(self, doc, url: str) -> Optional[str]:
@@ -99,17 +99,16 @@ class DagstuhlTranslator:
         # Add PDF attachment if available
         pdf_url = self._get_pdf_url(doc)
         if pdf_url:
-            item["attachments"].append({
-                "url": pdf_url,
-                "title": "Full Text PDF",
-                "mimeType": "application/pdf"
-            })
+            item["attachments"].append(
+                {
+                    "url": pdf_url,
+                    "title": "Full Text PDF",
+                    "mimeType": "application/pdf",
+                }
+            )
 
         # Add snapshot
-        item["attachments"].append({
-            "title": "Snapshot",
-            "mimeType": "text/html"
-        })
+        item["attachments"].append({"title": "Snapshot", "mimeType": "text/html"})
 
         item["libraryCatalog"] = "Dagstuhl Research Online Publication Server"
 
@@ -140,11 +139,7 @@ class DagstuhlTranslator:
         Returns:
             Item dictionary
         """
-        item = {
-            "creators": [],
-            "tags": [],
-            "attachments": []
-        }
+        item = {"creators": [], "tags": [], "attachments": []}
 
         # Would use BibTeX translator
         # Extract keywords from notes

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

@@ -31,7 +31,7 @@ class DarAlmandumahTranslator:
         "priority": 100,
         "inRepository": True,
         "translatorType": 4,  # Web
-        "lastUpdated": "2021-07-30 23:08:33"
+        "lastUpdated": "2021-07-30 23:08:33",
     }
 
     def detect_web(self, doc, url: str) -> Optional[str]:
@@ -88,7 +88,9 @@ class DarAlmandumahTranslator:
             return {}
 
         # Construct EndNote export URL
-        export_url = f"https://search.mandumah.com/Record/{record_id}/Export?style=EndNote"
+        export_url = (
+            f"https://search.mandumah.com/Record/{record_id}/Export?style=EndNote"
+        )
 
         # Fetch EndNote data
         # In real implementation, would fetch and parse
@@ -103,11 +105,13 @@ class DarAlmandumahTranslator:
         # Add PDF if available
         pdf_url = self._get_pdf_url(doc)
         if pdf_url:
-            item["attachments"].append({
-                "url": pdf_url,
-                "title": "Full Text PDF",
-                "mimeType": "application/pdf"
-            })
+            item["attachments"].append(
+                {
+                    "url": pdf_url,
+                    "title": "Full Text PDF",
+                    "mimeType": "application/pdf",
+                }
+            )
 
         return item
 
@@ -145,11 +149,11 @@ class DarAlmandumahTranslator:
             "itemType": "journalArticle",
             "creators": [],
             "tags": [],
-            "attachments": []
+            "attachments": [],
         }
 
         # Clean Arabic commas in author names
-        text = re.sub(r'^(\s*%[AEY].*)،', r'\1,', text, flags=re.MULTILINE)
+        text = re.sub(r"^(\s*%[AEY].*)،", r"\1,", text, flags=re.MULTILINE)
 
         # Would use Refer/BibIX translator
 

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

@@ -30,7 +30,7 @@ class DARTEuropeTranslator:
         "priority": 100,
         "inRepository": True,
         "translatorType": 4,  # Web
-        "lastUpdated": "2022-05-04 03:09:28"
+        "lastUpdated": "2022-05-04 03:09:28",
     }
 
     def detect_web(self, doc, url: str) -> Optional[str]:
@@ -80,12 +80,7 @@ class DARTEuropeTranslator:
         Returns:
             Scraped item data
         """
-        item = {
-            "itemType": "thesis",
-            "creators": [],
-            "tags": [],
-            "attachments": []
-        }
+        item = {"itemType": "thesis", "creators": [], "tags": [], "attachments": []}
 
         # Extract title
         title = self._get_field_value(doc, "Title")
@@ -125,11 +120,9 @@ class DARTEuropeTranslator:
         # Extract author
         author = self._get_field_value(doc, "Author")
         if author:
-            item["creators"].append({
-                "firstName": "",
-                "lastName": author,
-                "creatorType": "author"
-            })
+            item["creators"].append(
+                {"firstName": "", "lastName": author, "creatorType": "author"}
+            )
 
         # Extract subjects as tags
         subjects = self._get_field_value(doc, "Subject(s)")
@@ -142,17 +135,21 @@ class DARTEuropeTranslator:
         if fulltext:
             fulltext = fulltext.strip()
             if ".pdf" in fulltext.lower():
-                item["attachments"].append({
-                    "url": fulltext,
-                    "title": "Dart-Europe Full Text PDF",
-                    "mimeType": "application/pdf"
-                })
+                item["attachments"].append(
+                    {
+                        "url": fulltext,
+                        "title": "Dart-Europe Full Text PDF",
+                        "mimeType": "application/pdf",
+                    }
+                )
             elif fulltext.startswith("http"):
-                item["attachments"].append({
-                    "url": fulltext,
-                    "title": "DART-Europe Thesis Page",
-                    "mimeType": "text/html"
-                })
+                item["attachments"].append(
+                    {
+                        "url": fulltext,
+                        "title": "DART-Europe Thesis Page",
+                        "mimeType": "text/html",
+                    }
+                )
 
         item["url"] = url
         item["libraryCatalog"] = "DART-Europe"

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

@@ -30,7 +30,7 @@ class DataGovTranslator:
         "priority": 100,
         "inRepository": True,
         "translatorType": 4,  # Web
-        "lastUpdated": "2021-07-21 21:34:07"
+        "lastUpdated": "2021-07-21 21:34:07",
     }
 
     def detect_web(self, doc, url: str) -> Optional[str]:
@@ -88,7 +88,7 @@ class DataGovTranslator:
             "attachments": [],
             "language": "en",
             "url": url,
-            "libraryCatalog": "Data.gov"
+            "libraryCatalog": "Data.gov",
         }
 
         # Extract from Schema.org metadata

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

@@ -34,7 +34,7 @@ class DatabaryTranslator:
         "inRepository": True,
         "translatorType": 4,
         "browserSupport": "gcsibv",
-        "lastUpdated": "2023-04-19 16:49:05"
+        "lastUpdated": "2023-04-19 16:49:05",
     }
 
     def detect_web(self, doc: BeautifulSoup, url: str) -> str:
@@ -48,16 +48,18 @@ class DatabaryTranslator:
         Returns:
             'dataset' for volume pages, 'multiple' for search, empty string otherwise
         """
-        if '/volume/' in url:
-            return 'dataset'
-        elif '/search?q=' in url:
+        if "/volume/" in url:
+            return "dataset"
+        elif "/search?q=" in url:
             # Check if there are search results
-            rows = doc.select('h3.search-volume-result-title>a')
+            rows = doc.select("h3.search-volume-result-title>a")
             if rows:
-                return 'multiple'
-        return ''
+                return "multiple"
+        return ""
 
-    def get_search_results(self, doc: BeautifulSoup, check_only: bool = False) -> Optional[Dict[str, str]]:
+    def get_search_results(
+        self, doc: BeautifulSoup, check_only: bool = False
+    ) -> Optional[Dict[str, str]]:
         """
         Extract search results from the page.
 
@@ -69,17 +71,17 @@ class DatabaryTranslator:
             Dictionary mapping URLs to titles, or None if none found
         """
         items = {}
-        rows = doc.select('h3.search-volume-result-title>a')
+        rows = doc.select("h3.search-volume-result-title>a")
 
         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
 
@@ -98,7 +100,7 @@ class DatabaryTranslator:
         """
         page_type = self.detect_web(doc, url)
 
-        if page_type == 'multiple':
+        if page_type == "multiple":
             return self.get_search_results(doc, check_only=False)
         else:
             return self.scrape(doc, url)
@@ -114,32 +116,29 @@ class DatabaryTranslator:
         Returns:
             Dictionary containing dataset metadata
         """
-        item = {
-            'itemType': 'dataset',
-            'creators': [],
-            'tags': [],
-            'attachments': []
-        }
+        item = {"itemType": "dataset", "creators": [], "tags": [], "attachments": []}
 
         # Extract DOI from the citation panel
-        doi_link = doc.select_one('p.panel-overview-volume-citation>a')
+        doi_link = doc.select_one("p.panel-overview-volume-citation>a")
         if doi_link:
-            doi = doi_link.get('href', '').replace('https://doi.org/', '').replace('http://doi.org/', '')
+            doi = (
+                doi_link.get("href", "")
+                .replace("https://doi.org/", "")
+                .replace("http://doi.org/", "")
+            )
             if doi:
-                item['DOI'] = doi
+                item["DOI"] = doi
                 # Set repository info
-                item['repository'] = 'Databrary'
-                item['libraryCatalog'] = 'Databrary'
+                item["repository"] = "Databrary"
+                item["libraryCatalog"] = "Databrary"
 
                 # Note: In the original JS, this fetches RIS data from DataCite
                 # For Python implementation, we'd extract DOI and let the DOI resolver handle it
                 # or we could implement RIS fetching here
 
                 # Add snapshot attachment
-                item['attachments'].append({
-                    'title': 'Snapshot',
-                    'url': url,
-                    'mimeType': 'text/html'
-                })
+                item["attachments"].append(
+                    {"title": "Snapshot", "url": url, "mimeType": "text/html"}
+                )
 
         return item