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

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

@@ -33,18 +33,18 @@ class ChristianScienceMonitorTranslator:
         "inRepository": True,
         "translatorType": 4,
         "browserSupport": "gcsibv",
-        "lastUpdated": "2016-11-01 18:26:01"
+        "lastUpdated": "2016-11-01 18:26:01",
     }
 
     def detect_web(self, doc: BeautifulSoup, url: str) -> str:
         """Detect if page is an article or search results."""
-        if doc.select_one('h1#headline'):
-            return 'magazineArticle'
+        if doc.select_one("h1#headline"):
+            return "magazineArticle"
 
-        if '/content/search?' in url:
-            return 'multiple'
+        if "/content/search?" in url:
+            return "multiple"
 
-        return ''
+        return ""
 
     def do_web(self, doc: BeautifulSoup, url: str) -> Dict[str, Any]:
         """Extract article data."""
@@ -62,46 +62,44 @@ class ChristianScienceMonitorTranslator:
             Dictionary containing article metadata
         """
         item = {
-            'itemType': 'magazineArticle',
-            'creators': [],
-            'tags': [],
-            'attachments': [],
-            'url': url,
-            'ISSN': '0882-7729',
-            'publicationTitle': 'Christian Science Monitor'
+            "itemType": "magazineArticle",
+            "creators": [],
+            "tags": [],
+            "attachments": [],
+            "url": url,
+            "ISSN": "0882-7729",
+            "publicationTitle": "Christian Science Monitor",
         }
 
         # Title
-        headline = doc.select_one('h1#headline')
+        headline = doc.select_one("h1#headline")
         if headline:
-            item['title'] = headline.get_text().strip()
+            item["title"] = headline.get_text().strip()
 
         # Authors
-        author_meta = doc.find('meta', attrs={'name': 'sailthru.author'})
-        if author_meta and author_meta.get('content'):
-            author_text = author_meta['content']
+        author_meta = doc.find("meta", attrs={"name": "sailthru.author"})
+        if author_meta and author_meta.get("content"):
+            author_text = author_meta["content"]
             # Handle multiple authors
-            authors = [a.strip() for a in author_text.split(',')]
+            authors = [a.strip() for a in author_text.split(",")]
             for author in authors:
                 if author:
-                    item['creators'].append(self._clean_author(author))
+                    item["creators"].append(self._clean_author(author))
 
         # Date
-        date_elem = doc.select_one('time#date-published')
-        if date_elem and date_elem.get('datetime'):
-            item['date'] = date_elem['datetime']
+        date_elem = doc.select_one("time#date-published")
+        if date_elem and date_elem.get("datetime"):
+            item["date"] = date_elem["datetime"]
 
         # Abstract
-        summary = doc.select_one('h2#summary')
+        summary = doc.select_one("h2#summary")
         if summary:
-            item['abstractNote'] = summary.get_text().strip()
+            item["abstractNote"] = summary.get_text().strip()
 
         # Snapshot attachment
-        item['attachments'].append({
-            'title': 'CS Monitor Snapshot',
-            'mimeType': 'text/html',
-            'url': url
-        })
+        item["attachments"].append(
+            {"title": "CS Monitor Snapshot", "mimeType": "text/html", "url": url}
+        )
 
         return item
 
@@ -112,13 +110,9 @@ class ChristianScienceMonitorTranslator:
 
         if len(parts) >= 2:
             return {
-                'firstName': ' '.join(parts[:-1]),
-                'lastName': parts[-1],
-                'creatorType': 'author'
+                "firstName": " ".join(parts[:-1]),
+                "lastName": parts[-1],
+                "creatorType": "author",
             }
         else:
-            return {
-                'lastName': name,
-                'creatorType': 'author',
-                'fieldMode': True
-            }
+            return {"lastName": name, "creatorType": "author", "fieldMode": True}

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

@@ -34,7 +34,7 @@ class ColumbiaUniversityPressTranslator:
         "inRepository": True,
         "translatorType": 4,
         "browserSupport": "gcsibv",
-        "lastUpdated": "2016-09-10 11:35:07"
+        "lastUpdated": "2016-09-10 11:35:07",
     }
 
     def detect_web(self, doc: BeautifulSoup, url: str) -> str:
@@ -54,7 +54,9 @@ class ColumbiaUniversityPressTranslator:
             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.
 
@@ -67,10 +69,10 @@ class ColumbiaUniversityPressTranslator:
         """
         items = {}
         found = False
-        rows = doc.select('div.search-list h2 > a')
+        rows = doc.select("div.search-list h2 > 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
@@ -111,31 +113,33 @@ class ColumbiaUniversityPressTranslator:
             Dictionary containing book metadata
         """
         item = {
-            'itemType': 'book',
-            'creators': [],
-            'tags': [],
-            'attachments': [],
-            'notes': [],
-            'seeAlso': []
+            "itemType": "book",
+            "creators": [],
+            "tags": [],
+            "attachments": [],
+            "notes": [],
+            "seeAlso": [],
         }
 
         # Extract title
-        title_elem = doc.select_one('div.book-header h1.title')
+        title_elem = doc.select_one("div.book-header h1.title")
         if title_elem:
-            item['title'] = title_elem.get_text(strip=True)
+            item["title"] = title_elem.get_text(strip=True)
 
         # Extract book details
-        book_details = doc.select('div.book-header.pc-only p[class], div.book-details p[class]')
+        book_details = doc.select(
+            "div.book-header.pc-only p[class], div.book-details p[class]"
+        )
 
         for detail in book_details:
-            class_name = ' '.join(detail.get('class', []))
+            class_name = " ".join(detail.get("class", []))
             content = detail.get_text(strip=True)
 
-            if class_name == 'subtitle':
-                if 'title' in item:
-                    item['title'] = f"{item['title']}: {content}"
+            if class_name == "subtitle":
+                if "title" in item:
+                    item["title"] = f"{item['title']}: {content}"
 
-            elif class_name == 'author':
+            elif class_name == "author":
                 # Parse creators (authors, editors, translators)
                 creator_string = content
 
@@ -149,54 +153,58 @@ class ColumbiaUniversityPressTranslator:
                     pos_translators = len(creator_string)
 
                 # Extract authors
-                authors_str = creator_string[:min(pos_editors, pos_translators)]
-                authors = re.split(r'\band\b|,', authors_str)
+                authors_str = creator_string[: min(pos_editors, pos_translators)]
+                authors = re.split(r"\band\b|,", authors_str)
                 for author in authors:
                     author = author.strip()
                     if author:
-                        item['creators'].append(self._clean_author(author, "author"))
+                        item["creators"].append(self._clean_author(author, "author"))
 
                 # Extract editors
                 if pos_editors < len(creator_string):
                     editors_str = creator_string[pos_editors:pos_translators]
-                    editors_str = re.sub(r'Edited\s*(by)?', '', editors_str)
-                    editors = re.split(r'\band\b|,', editors_str)
+                    editors_str = re.sub(r"Edited\s*(by)?", "", editors_str)
+                    editors = re.split(r"\band\b|,", editors_str)
                     for editor in editors:
                         editor = editor.strip()
                         if editor:
-                            item['creators'].append(self._clean_author(editor, "editor"))
+                            item["creators"].append(
+                                self._clean_author(editor, "editor")
+                            )
 
                 # Extract translators
                 if pos_translators < len(creator_string):
                     translators_str = creator_string[pos_translators:]
-                    translators_str = re.sub(r'Translated\s*(by)?', '', translators_str)
-                    translators = re.split(r'\band\b|,', translators_str)
+                    translators_str = re.sub(r"Translated\s*(by)?", "", translators_str)
+                    translators = re.split(r"\band\b|,", translators_str)
                     for translator in translators:
                         translator = translator.strip()
                         if translator:
-                            item['creators'].append(self._clean_author(translator, "translator"))
+                            item["creators"].append(
+                                self._clean_author(translator, "translator")
+                            )
 
-            elif class_name == 'pubdate':
+            elif class_name == "pubdate":
                 # Convert date to ISO format
-                item['date'] = content
+                item["date"] = content
 
-            elif class_name == 'publisher':
-                item['publisher'] = content
+            elif class_name == "publisher":
+                item["publisher"] = content
 
-            elif class_name == 'isbn':
-                item['ISBN'] = content
+            elif class_name == "isbn":
+                item["ISBN"] = content
 
-            elif class_name == 'pages':
-                item['pages'] = content
+            elif class_name == "pages":
+                item["pages"] = content
 
         # If there is no publisher field, assume it's published by CUP
-        if 'publisher' not in item:
-            item['publisher'] = "Columbia University Press"
+        if "publisher" not in item:
+            item["publisher"] = "Columbia University Press"
 
         # Extract abstract
-        abstract_elem = doc.select_one('div.sp__the-description')
+        abstract_elem = doc.select_one("div.sp__the-description")
         if abstract_elem:
-            item['abstractNote'] = abstract_elem.get_text(strip=True)
+            item["abstractNote"] = abstract_elem.get_text(strip=True)
 
         return item
 
@@ -216,13 +224,9 @@ class ColumbiaUniversityPressTranslator:
 
         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/Common_Place.py

@@ -34,7 +34,7 @@ class CommonPlaceTranslator:
         "inRepository": True,
         "translatorType": 4,
         "browserSupport": "gcsibv",
-        "lastUpdated": "2016-09-10 09:34:34"
+        "lastUpdated": "2016-09-10 09:34:34",
     }
 
     def detect_web(self, doc: BeautifulSoup, url: str) -> str:
@@ -50,11 +50,16 @@ class CommonPlaceTranslator:
         """
         if self._get_search_results(doc, True):
             return "multiple"
-        elif "single-article" in doc.body.get('class', []) or "common-place-archives.org" in url:
+        elif (
+            "single-article" in doc.body.get("class", [])
+            or "common-place-archives.org" in url
+        ):
             return "journalArticle"
         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.
 
@@ -67,10 +72,10 @@ class CommonPlaceTranslator:
         """
         items = {}
         found = False
-        rows = doc.select('h3.article-title > a, h2 > a')
+        rows = doc.select("h3.article-title > a, h2 > 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
@@ -109,46 +114,46 @@ class CommonPlaceTranslator:
             Dictionary containing article metadata
         """
         item = {
-            'itemType': 'journalArticle',
-            'publicationTitle': 'Common-Place',
-            'url': url,
-            'creators': [],
-            'tags': [],
-            'attachments': [],
-            'notes': [],
-            'seeAlso': []
+            "itemType": "journalArticle",
+            "publicationTitle": "Common-Place",
+            "url": url,
+            "creators": [],
+            "tags": [],
+            "attachments": [],
+            "notes": [],
+            "seeAlso": [],
         }
 
-        if "single-article" in doc.body.get('class', []):
+        if "single-article" in doc.body.get("class", []):
             # New format
-            title_elem = doc.select_one('article h1')
+            title_elem = doc.select_one("article h1")
             if title_elem:
-                item['title'] = title_elem.get_text(strip=True)
+                item["title"] = title_elem.get_text(strip=True)
 
-            author_elem = doc.select_one('article h1 + p')
+            author_elem = doc.select_one("article h1 + p")
             if author_elem:
                 author = author_elem.get_text(strip=True)
-                item['creators'].append(self._clean_author(author, "author"))
+                item["creators"].append(self._clean_author(author, "author"))
 
-            abstract_elem = doc.select_one('article div.entry-excerpt')
+            abstract_elem = doc.select_one("article div.entry-excerpt")
             if abstract_elem:
-                item['abstractNote'] = abstract_elem.get_text(strip=True)
+                item["abstractNote"] = abstract_elem.get_text(strip=True)
 
             # Extract date from breadcrumb
-            date_elem = doc.select_one('article ol.breadcrumb li')
+            date_elem = doc.select_one("article ol.breadcrumb li")
             if date_elem:
                 # Get text nodes only
-                date_text = ''.join([t for t in date_elem.stripped_strings if t])
-                item['date'] = date_text
+                date_text = "".join([t for t in date_elem.stripped_strings if t])
+                item["date"] = date_text
 
             # Extract volume and issue
-            volno_elem = doc.select_one('article ol.breadcrumb li:first-child a')
+            volno_elem = doc.select_one("article ol.breadcrumb li:first-child a")
             if volno_elem:
                 volno = volno_elem.get_text(strip=True)
-                m = re.search(r'Vol\.\s*(\d+)\s+No\.\s*(\d+)', volno)
+                m = re.search(r"Vol\.\s*(\d+)\s+No\.\s*(\d+)", volno)
                 if m:
-                    item['volume'] = m.group(1)
-                    item['issue'] = m.group(2)
+                    item["volume"] = m.group(1)
+                    item["issue"] = m.group(2)
 
         else:
             # Old format
@@ -157,16 +162,16 @@ class CommonPlaceTranslator:
             date_re = r'<a href="/vol-(\d+)/no-(\d+)/">([^<]*)</a>'
             m = re.search(date_re, body_html)
             if m:
-                item['volume'] = m.group(1)
-                item['issue'] = m.group(2)
+                item["volume"] = m.group(1)
+                item["issue"] = m.group(2)
                 # Extract month and year from the third group
                 issue_info = m.group(3)
-                month_match = re.search(r'·\s*([\w\s]+)$', issue_info)
+                month_match = re.search(r"·\s*([\w\s]+)$", issue_info)
                 if month_match:
-                    item['date'] = month_match.group(1)
+                    item["date"] = month_match.group(1)
 
-            author = doc.select_one('div#content p span:nth-of-type(1)')
-            title = doc.select_one('div#content p span:nth-of-type(2)')
+            author = doc.select_one("div#content p span:nth-of-type(1)")
+            title = doc.select_one("div#content p span:nth-of-type(2)")
 
             if author and title:
                 author_text = author.get_text(strip=True)
@@ -177,34 +182,42 @@ class CommonPlaceTranslator:
                     title_text = "Review of " + title_text
                     author_text = author_text.replace("Review by", "").strip()
 
-                item['creators'].append(self._clean_author(author_text, "author"))
-                item['title'] = title_text
+                item["creators"].append(self._clean_author(author_text, "author"))
+                item["title"] = title_text
             else:
                 # Older issue format
-                review_elem = doc.select_one('body > table tr > td:nth-child(2) > p:nth-child(2)')
+                review_elem = doc.select_one(
+                    "body > table tr > td:nth-child(2) > p:nth-child(2)"
+                )
                 if review_elem and "Review" in review_elem.get_text():
-                    title_elem = doc.select_one('body > table tr > td:nth-child(2) > p i')
+                    title_elem = doc.select_one(
+                        "body > table tr > td:nth-child(2) > p i"
+                    )
                     if title_elem:
-                        item['title'] = "Review of " + title_elem.get_text(strip=True)
-                    author_text = review_elem.get_text()[10:].strip()  # Skip "Review by "
+                        item["title"] = "Review of " + title_elem.get_text(strip=True)
+                    author_text = review_elem.get_text()[
+                        10:
+                    ].strip()  # Skip "Review by "
                 else:
-                    title_elem = doc.select_one('body > table tr > td:nth-child(2) > p b')
+                    title_elem = doc.select_one(
+                        "body > table tr > td:nth-child(2) > p b"
+                    )
                     if title_elem:
-                        item['title'] = title_elem.get_text(strip=True)
-                    author_elem = doc.select_one('body > table tr > td:nth-child(2) > p:first-child')
+                        item["title"] = title_elem.get_text(strip=True)
+                    author_elem = doc.select_one(
+                        "body > table tr > td:nth-child(2) > p:first-child"
+                    )
                     if author_elem:
-                        lines = author_elem.get_text().split('\n')
+                        lines = author_elem.get_text().split("\n")
                         author_text = lines[1].strip() if len(lines) > 1 else ""
 
                 if author_text:
-                    item['creators'].append(self._clean_author(author_text, "author"))
+                    item["creators"].append(self._clean_author(author_text, "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
 
@@ -224,13 +237,9 @@ class CommonPlaceTranslator:
 
         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}