scitex 2.15.3__py3-none-any.whl → 2.16.0__py3-none-any.whl

scitex/scholar/url_finder/translators/_individual/lookus.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""LookUs translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class LookusTranslator(BaseTranslator):
+    """LookUs."""
+
+    LABEL = "LookUs"
+    URL_TARGET_PATTERN = r"/jvi.aspx[^#]*[?&](volume|issue|un)="
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/lulu.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Lulu translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class LuluTranslator(BaseTranslator):
+    """Lulu."""
+
+    LABEL = "Lulu"
+    URL_TARGET_PATTERN = r"^https?://www\.lulu\.com/shop/"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/lwn_net.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""LWN.net translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class LwnNetTranslator(BaseTranslator):
+    """LWN.net."""
+
+    LABEL = "LWN.net"
+    URL_TARGET_PATTERN = r"^https?://lwn\.net/"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/lww.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Lippincott Williams and Wilkins translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class LWWTranslator(BaseTranslator):
+    """Lippincott Williams and Wilkins."""
+
+    LABEL = "Lippincott Williams and Wilkins"
+    URL_TARGET_PATTERN = r"^https?://(www\.)?journals\.lww\.com/"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/mab2.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""MAB2 translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class Mab2Translator(BaseTranslator):
+    """MAB2."""
+
+    LABEL = "MAB2"
+    URL_TARGET_PATTERN = r"mab2"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/magazines_russ_ru.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""magazines.russ.ru translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class MagazinesRussRuTranslator(BaseTranslator):
+    """magazines.russ.ru."""
+
+    LABEL = "magazines.russ.ru"
+    URL_TARGET_PATTERN = r"^https?://magazines\.russ\.ru/[a-zA-Z -_]+/[0-9]+/[0-9]+/"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/mailman.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Mailman translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class MailmanTranslator(BaseTranslator):
+    """Mailman."""
+
+    LABEL = "Mailman"
+    URL_TARGET_PATTERN = r"/(pipermail|archives)/[A-Za-z0-9_-]*/[0-9]{4}-(January|February|March|April|May|June|July|August|September|October|November|December)/[0-9]{6}\.html"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/mainichi_daily_news.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Mainichi Daily News translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class MainichiDailyNewsTranslator(BaseTranslator):
+    """Mainichi Daily News."""
+
+    LABEL = "Mainichi Daily News"
+    URL_TARGET_PATTERN = r"^https?://mainichi\.jp/(?:english/)?(articles/|search\?)"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/marc.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""MARC translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class MarcTranslator(BaseTranslator):
+    """MARC."""
+
+    LABEL = "MARC"
+    URL_TARGET_PATTERN = r"marc"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/marcxml.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""MARCXML translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class MarcxmlTranslator(BaseTranslator):
+    """MARCXML."""
+
+    LABEL = "MARCXML"
+    URL_TARGET_PATTERN = r"xml"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/mastodon.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Mastodon translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class MastodonTranslator(BaseTranslator):
+    """Mastodon."""
+
+    LABEL = "Mastodon"
+    URL_TARGET_PATTERN = r"/@.+/\d{10}"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/matbugat_ru.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Matbugat.ru translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class MatbugatRuTranslator(BaseTranslator):
+    """Matbugat.ru."""
+
+    LABEL = "Matbugat.ru"
+    URL_TARGET_PATTERN = r"^https?://(www\.)?matbugat\.ru/"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

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

@@ -0,0 +1,25 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Max Planck Institute for the History of Science Virtual Laboratory Library translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import 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"
+    URL_TARGET_PATTERN = r"^https?://vlp\.mpiwg-berlin\.mpg\.de/library/"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/mcv.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""MCV translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class McvTranslator(BaseTranslator):
+    """MCV."""
+
+    LABEL = "MCV"
+    URL_TARGET_PATTERN = r"^https?://(www\.)?mcvuk\.com"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

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

@@ -0,0 +1,76 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""MDPI Journals translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class MDPITranslator(BaseTranslator):
+    """MDPI Journals."""
+
+    LABEL = "MDPI Journals"
+    URL_TARGET_PATTERN = r"^https?://www\.mdpi\.com"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        """Extract PDF URLs from MDPI article page.
+
+        Based on JavaScript translator (MDPI Journals.js).
+        MDPI uses embedded metadata for PDF links.
+        """
+        pdf_urls = []
+
+        # 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)
+            if pdf_url:
+                pdf_urls.append(pdf_url)
+                return pdf_urls
+        except:
+            pass
+
+        # 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)
+            if pdf_link:
+                # Make absolute URL if needed
+                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
+        except:
+            pass
+
+        # 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
+                # Try appending /pdf to current URL
+                pdf_url = f"{current_url.rstrip('/')}/pdf"
+                pdf_urls.append(pdf_url)
+                return pdf_urls
+        except:
+            pass
+
+        return pdf_urls
+
+
+# Demo usage
+# Note: Due to relative imports, run the demo script instead:
+# python scripts/demo_mdpi.py

scitex/scholar/url_finder/translators/_individual/mdpi_journals.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""MDPI Journals translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class MdpiJournalsTranslator(BaseTranslator):
+    """MDPI Journals."""
+
+    LABEL = "MDPI Journals"
+    URL_TARGET_PATTERN = r"^https?://www\.mdpi\.com"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/medes.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""medes translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class MedesTranslator(BaseTranslator):
+    """medes."""
+
+    LABEL = "medes"
+    URL_TARGET_PATTERN = r"^https?://(www\.)?medes\.com/"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/medium.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Medium translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class MediumTranslator(BaseTranslator):
+    """Medium."""
+
+    LABEL = "Medium"
+    URL_TARGET_PATTERN = r"^https?://([^.]+\.)?medium\.com"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/medline_nbib.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""MEDLINE/nbib translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class MEDLINEnbibTranslator(BaseTranslator):
+    """MEDLINE/nbib."""
+
+    LABEL = "MEDLINE/nbib"
+    URL_TARGET_PATTERN = r"txt"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/medlinenbib.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""MEDLINEnbib translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class MedlinenbibTranslator(BaseTranslator):
+    """MEDLINEnbib."""
+
+    LABEL = "MEDLINEnbib"
+    URL_TARGET_PATTERN = r"txt"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/medra.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""mEDRA translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class MedraTranslator(BaseTranslator):
+    """mEDRA."""
+
+    LABEL = "mEDRA"
+    URL_TARGET_PATTERN = r"^https?://www\.medra\.org/servlet/view\?"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/metalib.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""MetaLib translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class MetalibTranslator(BaseTranslator):
+    """MetaLib."""
+
+    LABEL = "MetaLib"
+    URL_TARGET_PATTERN = r"^https?://[^/]*/V/"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/mets.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""METS translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class MetsTranslator(BaseTranslator):
+    """METS."""
+
+    LABEL = "METS"
+    URL_TARGET_PATTERN = r"xml"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

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

@@ -0,0 +1,25 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Microbiology Society Journals translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class MicrobiologySocietyJournalsTranslator(BaseTranslator):
+    """Microbiology Society Journals."""
+
+    LABEL = "Microbiology Society Journals"
+    URL_TARGET_PATTERN = (
+        r"^https?://(www\.)?(\w)+\.microbiologyresearch\.org/(content/journal/|search?)"
+    )
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []

scitex/scholar/url_finder/translators/_individual/microsoft_academic.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Microsoft Academic translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from .._core.base import BaseTranslator
+
+
+class MicrosoftAcademicTranslator(BaseTranslator):
+    """Microsoft Academic."""
+
+    LABEL = "Microsoft Academic"
+    URL_TARGET_PATTERN = r"^https?://academic\.microsoft\.com"
+
+    @classmethod
+    def matches_url(cls, url: str) -> bool:
+        return bool(re.match(cls.URL_TARGET_PATTERN, url))
+
+    @classmethod
+    async def extract_pdf_urls_async(cls, page: Page) -> List[str]:
+        return []