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

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

@@ -34,7 +34,7 @@ class DAIZenonTranslator:
         "inRepository": True,
         "translatorType": 4,
         "browserSupport": "gcsibv",
-        "lastUpdated": "2020-10-13 15:24:32"
+        "lastUpdated": "2020-10-13 15:24:32",
     }
 
     def detect_web(self, doc: BeautifulSoup, url: str) -> str:
@@ -45,14 +45,16 @@ class DAIZenonTranslator:
             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.select('div.row a.title')
+        rows = doc.select("div.row a.title")
 
         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
@@ -76,22 +78,17 @@ class DAIZenonTranslator:
         Note: This is a simplified version. The full translator requires
         MARC processing which is complex in Python.
         """
-        item = {
-            'itemType': 'book',
-            'creators': [],
-            'tags': [],
-            'attachments': []
-        }
+        item = {"itemType": "book", "creators": [], "tags": [], "attachments": []}
 
         # Extract title
-        title_elem = doc.select_one('h1.title, .record-title')
+        title_elem = doc.select_one("h1.title, .record-title")
         if title_elem:
-            item['title'] = title_elem.get_text(strip=True)
+            item["title"] = title_elem.get_text(strip=True)
 
         # Extract metadata from table rows
-        for row in doc.select('table tr'):
-            label_elem = row.find('th')
-            value_elem = row.find('td')
+        for row in doc.select("table tr"):
+            label_elem = row.find("th")
+            value_elem = row.find("td")
 
             if not label_elem or not value_elem:
                 continue
@@ -99,63 +96,65 @@ class DAIZenonTranslator:
             label = label_elem.get_text(strip=True)
             value = value_elem.get_text(strip=True)
 
-            if label == 'Author' or label == 'Creator':
-                parts = value.split(',')
+            if label == "Author" or label == "Creator":
+                parts = value.split(",")
                 if len(parts) >= 2:
-                    item['creators'].append({
-                        'firstName': parts[1].strip(),
-                        'lastName': parts[0].strip(),
-                        'creatorType': 'author'
-                    })
+                    item["creators"].append(
+                        {
+                            "firstName": parts[1].strip(),
+                            "lastName": parts[0].strip(),
+                            "creatorType": "author",
+                        }
+                    )
                 else:
-                    item['creators'].append({
-                        'lastName': value,
-                        'creatorType': 'author',
-                        'fieldMode': True
-                    })
+                    item["creators"].append(
+                        {"lastName": value, "creatorType": "author", "fieldMode": True}
+                    )
 
-            elif label == 'Publication Date' or label == 'Year':
-                item['date'] = value
+            elif label == "Publication Date" or label == "Year":
+                item["date"] = value
 
-            elif label == 'Publisher':
-                item['publisher'] = value
+            elif label == "Publisher":
+                item["publisher"] = value
 
-            elif label == 'Place of Publication' or label == 'Place':
-                item['place'] = value
+            elif label == "Place of Publication" or label == "Place":
+                item["place"] = value
 
-            elif label == 'Series':
-                item['series'] = value
+            elif label == "Series":
+                item["series"] = value
 
-            elif label == 'Pages' or label == 'Extent':
-                item['numPages'] = re.sub(r'\s*p\.?$', '', value)
+            elif label == "Pages" or label == "Extent":
+                item["numPages"] = re.sub(r"\s*p\.?$", "", value)
 
-            elif label == 'ISBN':
-                item['ISBN'] = value
+            elif label == "ISBN":
+                item["ISBN"] = value
 
-            elif label == 'Language':
-                item['language'] = value
+            elif label == "Language":
+                item["language"] = value
 
-            elif label == 'Call Number':
-                item['callNumber'] = value
+            elif label == "Call Number":
+                item["callNumber"] = value
 
         # Extract tags/subjects
-        for tag_elem in doc.select('.subjects a, .tags a'):
+        for tag_elem in doc.select(".subjects a, .tags a"):
             tag_text = tag_elem.get_text(strip=True)
             if tag_text:
-                item['tags'].append({'tag': tag_text})
+                item["tags"].append({"tag": tag_text})
 
         # Extract abstract/description
-        abstract_elem = doc.select_one('.description, .abstract')
+        abstract_elem = doc.select_one(".description, .abstract")
         if abstract_elem:
-            item['abstractNote'] = abstract_elem.get_text(strip=True)
+            item["abstractNote"] = abstract_elem.get_text(strip=True)
 
         # Add attachment
-        clean_url = re.sub(r'#.*', '', url)
-        item['attachments'].append({
-            'url': clean_url,
-            'title': 'DAI Zenon Entry',
-            'mimeType': 'text/html',
-            'snapshot': False
-        })
+        clean_url = re.sub(r"#.*", "", url)
+        item["attachments"].append(
+            {
+                "url": clean_url,
+                "title": "DAI Zenon Entry",
+                "mimeType": "text/html",
+                "snapshot": False,
+            }
+        )
 
         return item

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

@@ -81,10 +81,10 @@ class AccessMedicineTranslator(BaseTranslator):
             "bookSection" for content pages,
             None otherwise
         """
-        if re.search(r'/searchresults', url, re.IGNORECASE):
+        if re.search(r"/searchresults", url, re.IGNORECASE):
             return "multiple"
 
-        if re.search(r'/content', url, re.IGNORECASE):
+        if re.search(r"/content", url, re.IGNORECASE):
             return "bookSection"
 
         return None
@@ -133,16 +133,13 @@ class AccessMedicineTranslator(BaseTranslator):
         }
 
         if content_type == "bookSection":
-            section_id_match = re.search(
-                r'sectionid=([^&]+)',
-                url.lower()
-            )
+            section_id_match = re.search(r"sectionid=([^&]+)", url.lower())
             if section_id_match:
                 metadata["section_id"] = section_id_match.group(1)
 
             try:
                 chapter_element = await page.query_selector(
-                    '#pageContent_lblChapterTitle1'
+                    "#pageContent_lblChapterTitle1"
                 )
                 if chapter_element:
                     chapter_text = await chapter_element.inner_html()
@@ -150,7 +147,7 @@ class AccessMedicineTranslator(BaseTranslator):
             except Exception:
                 pass
 
-            base_url = re.sub(r'/content.*', '', url, flags=re.IGNORECASE)
+            base_url = re.sub(r"/content.*", "", url, flags=re.IGNORECASE)
             if "section_id" in metadata:
                 citation_url = (
                     f"{base_url}/downloadCitation.aspx?"
@@ -161,52 +158,49 @@ class AccessMedicineTranslator(BaseTranslator):
         elif content_type == "multiple":
             try:
                 entries = await page.query_selector_all(
-                    'div.search-entries > div.row-fluid.bordered-bottom > div.span10'
+                    "div.search-entries > div.row-fluid.bordered-bottom > div.span10"
                 )
 
                 results = []
                 for entry in entries:
                     try:
-                        title_element = await entry.query_selector('h3')
+                        title_element = await entry.query_selector("h3")
                         if not title_element:
                             continue
                         title = await title_element.text_content()
                         title = title.strip()
 
-                        book_element = await entry.query_selector('p')
+                        book_element = await entry.query_selector("p")
                         book_title = ""
                         if book_element:
                             book_title = await book_element.text_content()
                             book_title = book_title.strip()
 
-                        link_element = await title_element.query_selector('a')
+                        link_element = await title_element.query_selector("a")
                         if link_element:
-                            href = await link_element.get_attribute('href')
+                            href = await link_element.get_attribute("href")
                             if href:
-                                begin_cut = href.find('=')
-                                end_cut = href.find('&')
+                                begin_cut = href.find("=")
+                                end_cut = href.find("&")
                                 if begin_cut != -1:
                                     if end_cut != -1:
-                                        section_id = href[begin_cut + 1:end_cut]
+                                        section_id = href[begin_cut + 1 : end_cut]
                                     else:
-                                        section_id = href[begin_cut + 1:]
+                                        section_id = href[begin_cut + 1 :]
 
                                     combined_title = f"{title} ({book_title})"
-                                    results.append({
-                                        "title": combined_title,
-                                        "section_id": section_id,
-                                    })
+                                    results.append(
+                                        {
+                                            "title": combined_title,
+                                            "section_id": section_id,
+                                        }
+                                    )
                     except Exception:
                         continue
 
                 metadata["search_results"] = results
 
-                base_url = re.sub(
-                    r'/searchresults.*',
-                    '',
-                    url,
-                    flags=re.IGNORECASE
-                )
+                base_url = re.sub(r"/searchresults.*", "", url, flags=re.IGNORECASE)
                 metadata["base_citation_url"] = (
                     f"{base_url}/downloadCitation.aspx?format=ris&sectionid="
                 )
@@ -227,8 +221,8 @@ class AccessMedicineTranslator(BaseTranslator):
         Returns:
             Cleaned abstract text
         """
-        cleaned = abstract.replace('.', '. ')
-        cleaned = re.sub(r'\s+', ' ', cleaned)
+        cleaned = abstract.replace(".", ". ")
+        cleaned = re.sub(r"\s+", " ", cleaned)
         return cleaned.strip()
 
     @classmethod
@@ -243,16 +237,16 @@ class AccessMedicineTranslator(BaseTranslator):
         Returns:
             Tuple of (cleaned_book_title, edition_number)
         """
-        if ',' not in book_title:
+        if "," not in book_title:
             return book_title, None
 
-        parts = book_title.split(',')
+        parts = book_title.split(",")
         last_part = parts[-1].strip()
 
-        edition_match = re.match(r'(\d+)e?$', last_part)
+        edition_match = re.match(r"(\d+)e?$", last_part)
         if edition_match:
             edition = edition_match.group(1)
-            new_title = ','.join(parts[:-1])
+            new_title = ",".join(parts[:-1])
             return new_title, edition
 
         return book_title, None

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

@@ -8,4 +8,4 @@ Kept for backward compatibility with existing registry imports.
 
 from .acm_digital_library import ACMDigitalLibraryTranslator as ACMTranslator
 
-__all__ = ['ACMTranslator']
+__all__ = ["ACMTranslator"]

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

@@ -51,8 +51,7 @@ class ACMDigitalLibraryTranslator(BaseTranslator):
 
         Based on JavaScript isContentUrl() (lines 101-103).
         """
-        return (('/doi/' in url or '/do/' in url) and
-                '/doi/proceedings' not in url)
+        return ("/doi/" in url or "/do/" in url) and "/doi/proceedings" not in url
 
     @classmethod
     async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
@@ -90,12 +89,14 @@ class ACMDigitalLibraryTranslator(BaseTranslator):
             # Method 1: Look for "View PDF" link on page (JS lines 170-176)
             # JavaScript: let pdfElement = doc.querySelector('a[title="View PDF"]');
             try:
-                pdf_link = await page.locator('a[title="View PDF"]').first.get_attribute('href', timeout=2000)
+                pdf_link = await page.locator(
+                    'a[title="View PDF"]'
+                ).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://dl.acm.org{pdf_link}"
-                    elif not pdf_link.startswith('http'):
+                    elif not pdf_link.startswith("http"):
                         pdf_link = f"https://dl.acm.org/{pdf_link}"
                     pdf_urls.append(pdf_link)
                     return pdf_urls
@@ -105,7 +106,9 @@ class ACMDigitalLibraryTranslator(BaseTranslator):
             # Method 2: Construct PDF URL from DOI (JS lines 132-133)
             # JavaScript: let doi = attr(doc, 'input[name=doiVal]', 'value');
             try:
-                doi = await page.locator('input[name=doiVal]').first.get_attribute('value', timeout=2000)
+                doi = await page.locator("input[name=doiVal]").first.get_attribute(
+                    "value", timeout=2000
+                )
                 if doi:
                     # ACM PDF URLs follow pattern: /doi/pdf/{DOI}
                     # Clean DOI and construct PDF URL
@@ -119,7 +122,7 @@ class ACMDigitalLibraryTranslator(BaseTranslator):
             # Method 3: Extract DOI from URL and construct PDF link
             try:
                 # Match patterns: /doi/10.1145/... or /doi/abs/10.1145/...
-                doi_match = re.search(r'/doi/(abs/)?(10\.[^?#/]+/[^?#/]+)', current_url)
+                doi_match = re.search(r"/doi/(abs/)?(10\.[^?#/]+/[^?#/]+)", current_url)
                 if doi_match:
                     doi = doi_match.group(2)
                     pdf_url = f"https://dl.acm.org/doi/pdf/{quote(doi, safe='')}"
@@ -130,11 +133,13 @@ class ACMDigitalLibraryTranslator(BaseTranslator):
 
             # Method 4: Look for any PDF download link
             try:
-                pdf_link = await page.locator('a[href*="/pdf/"], a[href*=".pdf"]').first.get_attribute('href', timeout=2000)
+                pdf_link = await page.locator(
+                    'a[href*="/pdf/"], a[href*=".pdf"]'
+                ).first.get_attribute("href", timeout=2000)
                 if pdf_link:
-                    if pdf_link.startswith('/'):
+                    if pdf_link.startswith("/"):
                         pdf_link = f"https://dl.acm.org{pdf_link}"
-                    elif not pdf_link.startswith('http'):
+                    elif not pdf_link.startswith("http"):
                         pdf_link = f"https://dl.acm.org/{pdf_link}"
                     pdf_urls.append(pdf_link)
                     return pdf_urls
@@ -180,16 +185,18 @@ class ACMDigitalLibraryTranslator(BaseTranslator):
 
             # Extract DOI (JS lines 132-133)
             try:
-                doi = await page.locator('input[name=doiVal]').first.get_attribute('value', timeout=2000)
+                doi = await page.locator("input[name=doiVal]").first.get_attribute(
+                    "value", timeout=2000
+                )
                 if doi:
-                    metadata['doi'] = doi.strip()
+                    metadata["doi"] = doi.strip()
             except Exception:
                 # Try from URL
-                doi_match = re.search(r'/doi/(abs/)?(10\.[^?#/]+/[^?#/]+)', current_url)
+                doi_match = re.search(r"/doi/(abs/)?(10\.[^?#/]+/[^?#/]+)", current_url)
                 if doi_match:
-                    metadata['doi'] = doi_match.group(2)
+                    metadata["doi"] = doi_match.group(2)
 
-            if not metadata.get('doi'):
+            if not metadata.get("doi"):
                 return None
 
             # Fetch CSL JSON metadata from ACM API (JS lines 133-139)
@@ -199,122 +206,145 @@ class ACMDigitalLibraryTranslator(BaseTranslator):
 
             # Extract item type from page context (JS lines 95-99)
             try:
-                pb_context = await page.locator('meta[name=pbContext]').first.get_attribute('content', timeout=2000)
+                pb_context = await page.locator(
+                    "meta[name=pbContext]"
+                ).first.get_attribute("content", timeout=2000)
                 if pb_context:
                     # JavaScript: let subtypeRegex = /csubtype:string:(\w+)/;
-                    subtype_match = re.search(r'csubtype:string:(\w+)', pb_context)
+                    subtype_match = re.search(r"csubtype:string:(\w+)", pb_context)
                     if subtype_match:
                         subtype = subtype_match.group(1).lower()
 
                         # Determine item type (JS lines 38-80)
-                        if subtype == 'conference':
-                            metadata['itemType'] = 'conferencePaper'
-                        elif subtype in ['journal', 'periodical', 'magazine', 'newsletter']:
-                            metadata['itemType'] = 'journalArticle'
-                        elif subtype in ['report', 'rfc']:
-                            metadata['itemType'] = 'report'
-                        elif subtype == 'thesis':
-                            metadata['itemType'] = 'thesis'
-                        elif subtype == 'software':
-                            metadata['itemType'] = 'computerProgram'
-                        elif subtype == 'dataset':
-                            metadata['itemType'] = 'document'
-                        elif subtype == 'book':
+                        if subtype == "conference":
+                            metadata["itemType"] = "conferencePaper"
+                        elif subtype in [
+                            "journal",
+                            "periodical",
+                            "magazine",
+                            "newsletter",
+                        ]:
+                            metadata["itemType"] = "journalArticle"
+                        elif subtype in ["report", "rfc"]:
+                            metadata["itemType"] = "report"
+                        elif subtype == "thesis":
+                            metadata["itemType"] = "thesis"
+                        elif subtype == "software":
+                            metadata["itemType"] = "computerProgram"
+                        elif subtype == "dataset":
+                            metadata["itemType"] = "document"
+                        elif subtype == "book":
                             # Check if it's a book or book section (JS lines 64-72)
-                            book_type_match = re.search(r'page:string:([\w ]+)', pb_context)
-                            if book_type_match and book_type_match.group(1).lower() == 'book page':
-                                metadata['itemType'] = 'book'
+                            book_type_match = re.search(
+                                r"page:string:([\w ]+)", pb_context
+                            )
+                            if (
+                                book_type_match
+                                and book_type_match.group(1).lower() == "book page"
+                            ):
+                                metadata["itemType"] = "book"
                             else:
-                                metadata['itemType'] = 'bookSection'
+                                metadata["itemType"] = "bookSection"
                         else:
-                            metadata['itemType'] = 'journalArticle'
+                            metadata["itemType"] = "journalArticle"
                     else:
-                        metadata['itemType'] = 'journalArticle'
+                        metadata["itemType"] = "journalArticle"
             except Exception:
-                metadata['itemType'] = 'journalArticle'
+                metadata["itemType"] = "journalArticle"
 
             # Extract title (JS line 162)
             try:
-                title = await page.locator('h1.citation__title').first.text_content(timeout=2000)
+                title = await page.locator("h1.citation__title").first.text_content(
+                    timeout=2000
+                )
                 if title:
-                    metadata['title'] = title.strip()
+                    metadata["title"] = title.strip()
             except Exception:
                 pass
 
             # Extract authors (JS lines 201-209)
             try:
-                author_elements = await page.locator('div.citation span.loa__author-name').all()
+                author_elements = await page.locator(
+                    "div.citation span.loa__author-name"
+                ).all()
                 if author_elements:
                     authors = []
                     for author_elem in author_elements:
                         author_name = await author_elem.text_content()
                         if author_name:
                             # Simple split on last space for first/last name
-                            name_parts = author_name.strip().rsplit(' ', 1)
+                            name_parts = author_name.strip().rsplit(" ", 1)
                             if len(name_parts) == 2:
-                                authors.append({
-                                    'firstName': name_parts[0],
-                                    'lastName': name_parts[1]
-                                })
+                                authors.append(
+                                    {
+                                        "firstName": name_parts[0],
+                                        "lastName": name_parts[1],
+                                    }
+                                )
                             else:
-                                authors.append({
-                                    'firstName': '',
-                                    'lastName': name_parts[0]
-                                })
-                    metadata['authors'] = authors
+                                authors.append(
+                                    {"firstName": "", "lastName": name_parts[0]}
+                                )
+                    metadata["authors"] = authors
             except Exception:
                 pass
 
             # Extract abstract (JS lines 164-168)
             try:
-                abstract_elements = await page.locator('div.article__abstract p, div.abstractSection p').all()
+                abstract_elements = await page.locator(
+                    "div.article__abstract p, div.abstractSection p"
+                ).all()
                 if abstract_elements:
                     abstract_texts = []
                     for elem in abstract_elements:
                         text = await elem.text_content()
                         if text:
                             abstract_texts.append(text.strip())
-                    abstract = '\n\n'.join(abstract_texts)
-                    if abstract and abstract.lower() != 'no abstract available.':
-                        metadata['abstract'] = abstract
+                    abstract = "\n\n".join(abstract_texts)
+                    if abstract and abstract.lower() != "no abstract available.":
+                        metadata["abstract"] = abstract
             except Exception:
                 pass
 
             # Extract publication title (JS lines 182-188)
             try:
-                pub_title = await page.locator('span.epub-section__title').first.text_content(timeout=2000)
+                pub_title = await page.locator(
+                    "span.epub-section__title"
+                ).first.text_content(timeout=2000)
                 if pub_title:
-                    metadata['publicationTitle'] = pub_title.strip()
+                    metadata["publicationTitle"] = pub_title.strip()
             except Exception:
                 pass
 
             # Extract tags/keywords (JS lines 222-225)
             try:
-                tag_elements = await page.locator('div.tags-widget a').all()
+                tag_elements = await page.locator("div.tags-widget a").all()
                 if tag_elements:
                     tags = []
                     for tag_elem in tag_elements:
                         tag_text = await tag_elem.text_content()
                         if tag_text:
                             tags.append(tag_text.strip())
-                    metadata['tags'] = tags
+                    metadata["tags"] = tags
             except Exception:
                 pass
 
             # Extract number of pages (JS lines 217-220)
             try:
-                num_pages = await page.locator('div.pages-info span').first.text_content(timeout=2000)
+                num_pages = await page.locator(
+                    "div.pages-info span"
+                ).first.text_content(timeout=2000)
                 if num_pages:
-                    metadata['numPages'] = num_pages.strip()
+                    metadata["numPages"] = num_pages.strip()
             except Exception:
                 pass
 
             # Construct clean URL (JS lines 177-179)
-            if metadata.get('doi'):
-                metadata['url'] = f"https://dl.acm.org/doi/{metadata['doi']}"
+            if metadata.get("doi"):
+                metadata["url"] = f"https://dl.acm.org/doi/{metadata['doi']}"
 
             # Set library catalog
-            metadata['libraryCatalog'] = 'ACM Digital Library'
+            metadata["libraryCatalog"] = "ACM Digital Library"
 
             return metadata
 

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

@@ -12,7 +12,9 @@ class AiritiTranslator(BaseTranslator):
     """Airiti."""
 
     LABEL = "Airiti"
-    URL_TARGET_PATTERN = r"^https?://([^/]+\.)?airitilibrary\.com/Publication/alDetailedMesh"
+    URL_TARGET_PATTERN = (
+        r"^https?://([^/]+\.)?airitilibrary\.com/Publication/alDetailedMesh"
+    )
 
     @classmethod
     def matches_url(cls, url: str) -> bool:

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

@@ -11,7 +11,9 @@ from ..core.base import BaseTranslator
 class AOSICTranslator(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/archive_ouverte_aosic.py

@@ -11,7 +11,9 @@ from ..core.base import BaseTranslator
 class ArchiveOuverteAOSICTranslator(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