scitex 2.14.0__py3-none-any.whl

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

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""The Telegraph translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class TheTelegraphTranslator(BaseTranslator):
+    """The Telegraph."""
+
+    LABEL = "The Telegraph"
+    URL_TARGET_PATTERN = r"^https?://[^/]*telegraph\.co\.uk/"
+
+    @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/the_times_and_sunday_times.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""The Times and Sunday Times translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class TheTimesAndSundayTimesTranslator(BaseTranslator):
+    """The Times and Sunday Times."""
+
+    LABEL = "The Times and Sunday Times"
+    URL_TARGET_PATTERN = r"^https?://www\.thetimes\.co\.uk/"
+
+    @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/the_times_of_israel.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""The Times of Israel translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class TheTimesOfIsraelTranslator(BaseTranslator):
+    """The Times of Israel."""
+
+    LABEL = "The Times of Israel"
+    URL_TARGET_PATTERN = r"https?://(www\.)?timesofisrael\.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/themarker.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""TheMarker translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class ThemarkerTranslator(BaseTranslator):
+    """TheMarker."""
+
+    LABEL = "TheMarker"
+    URL_TARGET_PATTERN = r"^https?://www\.themarker\.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/theory_of_computing.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Theory of Computing translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class TheoryOfComputingTranslator(BaseTranslator):
+    """Theory of Computing."""
+
+    LABEL = "Theory of Computing"
+    URL_TARGET_PATTERN = r"^https?://(theoryofcomputing\.org|toc\.cse\.iitk\.ac\.in|www\.cims\.nyu\.edu/~regev/toc|toc\.ilab\.sztaki\.hu|toc\.nada\.kth\.se|tocmirror\.cs\.tau\.ac\.il)/articles/[vg].*(/|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/thesesfr.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""ThesesFR translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class ThesesfrTranslator(BaseTranslator):
+    """ThesesFR."""
+
+    LABEL = "ThesesFR"
+    URL_TARGET_PATTERN = r"^https?://(www\.)?theses\.fr/([a-z]{2}/)?((s\d+|\d{4}.{8}|\d{8}X|\d{9})(?!\.(rdf|xml)$)|(sujets/\?q=|\?q=))(?!.*&format=(json|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/thieme.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Thieme translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class ThiemeTranslator(BaseTranslator):
+    """Thieme."""
+
+    LABEL = "Thieme"
+    URL_TARGET_PATTERN = r"^https?://(www\.)?thieme-connect\.(com|de)/products/"
+
+    @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/time_com.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Time.com translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class TimeComTranslator(BaseTranslator):
+    """Time.com."""
+
+    LABEL = "Time.com"
+    URL_TARGET_PATTERN = r"^https?://([^/]*\.)?time\.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/timesmachine.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""TimesMachine translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class TimesmachineTranslator(BaseTranslator):
+    """TimesMachine."""
+
+    LABEL = "TimesMachine"
+    URL_TARGET_PATTERN = r"^https?://timesmachine\.nytimes\.com/timesmachine/"
+
+    @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/tony_blair_institute.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Tony Blair Institute for Global Change translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class TonyBlairInstituteTranslator(BaseTranslator):
+    """Tony Blair Institute for Global Change."""
+
+    LABEL = "Tony Blair Institute for Global Change"
+    URL_TARGET_PATTERN = r"^https://institute\.global/"
+
+    @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/tony_blair_institute_for_global_change.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Tony Blair Institute for Global Change translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class TonyBlairInstituteForGlobalChangeTranslator(BaseTranslator):
+    """Tony Blair Institute for Global Change."""
+
+    LABEL = "Tony Blair Institute for Global Change"
+    URL_TARGET_PATTERN = r"^https://institute\.global/"
+
+    @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/toronto_star.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Toronto Star translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class TorontoStarTranslator(BaseTranslator):
+    """Toronto Star."""
+
+    LABEL = "Toronto Star"
+    URL_TARGET_PATTERN = r"^https?://www\.thestar\.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/transportation_research_board.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Transportation Research Board translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class TransportationResearchBoardTranslator(BaseTranslator):
+    """Transportation Research Board."""
+
+    LABEL = "Transportation Research Board"
+    URL_TARGET_PATTERN = r"^https?://(www|trid)\.trb\.org/"
+
+    @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/treesearch.py

@@ -0,0 +1,25 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Treesearch translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class TreesearchTranslator(BaseTranslator):
+    """Treesearch."""
+
+    LABEL = "Treesearch"
+    URL_TARGET_PATTERN = (
+        r"^https?://([^/]+\.)?treesearch\.fs\.fed\.us/(pubs/\d+$|search\.php)"
+    )
+
+    @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/trove.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Trove translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class TroveTranslator(BaseTranslator):
+    """Trove."""
+
+    LABEL = "Trove"
+    URL_TARGET_PATTERN = r"^https?://trove\.nla\.gov\.au/(?:newspaper|gazette|work|book|article|picture|music|map|collection|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/tumblr.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Tumblr translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class TumblrTranslator(BaseTranslator):
+    """Tumblr."""
+
+    LABEL = "Tumblr"
+    URL_TARGET_PATTERN = r"^https?://[^/]+\.tumblr\.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/tv_by_the_numbers.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""TV by the Numbers translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class TvByTheNumbersTranslator(BaseTranslator):
+    """TV by the Numbers."""
+
+    LABEL = "TV by the Numbers"
+    URL_TARGET_PATTERN = r"^https?://tvbythenumbers\.zap2it\.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/tvnz.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""TVNZ translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class TvnzTranslator(BaseTranslator):
+    """TVNZ."""
+
+    LABEL = "TVNZ"
+    URL_TARGET_PATTERN = r"^https?://(www\.)?tvnz\.co\.nz/one-news/"
+
+    @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/twitter.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Twitter translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class TwitterTranslator(BaseTranslator):
+    """Twitter."""
+
+    LABEL = "Twitter"
+    URL_TARGET_PATTERN = r"^https?://([^/]+\.)?(twitter|x)\.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/ubiquity_journals.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Ubiquity Journals translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class UbiquityJournalsTranslator(BaseTranslator):
+    """Ubiquity Journals."""
+
+    LABEL = "Ubiquity Journals"
+    URL_TARGET_PATTERN = r"^https?://[^/]+(/articles/10\.\d{4,9}/[-._;()/:a-z0-9A-Z]+|/articles/?$|/\d+/volume/\d+/issue/\d+)"
+
+    @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/uchicago_vufind.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""UChicago VuFind translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class UchicagoVufindTranslator(BaseTranslator):
+    """UChicago VuFind."""
+
+    LABEL = "UChicago VuFind"
+    URL_TARGET_PATTERN = r"^https?://([^/]+\.)?lib\.uchicago\.edu/"
+
+    @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/unapi.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""unAPI translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class UnapiTranslator(BaseTranslator):
+    """unAPI."""
+
+    LABEL = "unAPI"
+    URL_TARGET_PATTERN = r"^$"
+
+    @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/unesco.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""UNESCO translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class UNESCOTranslator(BaseTranslator):
+    """UNESCO."""
+
+    LABEL = "UNESCO"
+    URL_TARGET_PATTERN = r"^https?://(www\.)?(unesco\.org|unesdoc\.unesco\.org)"
+
+    @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/university_of_california_press_books.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""University of California Press Books translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class UniversityOfCaliforniaPressBooksTranslator(BaseTranslator):
+    """University of California Press Books."""
+
+    LABEL = "University of California Press Books"
+    URL_TARGET_PATTERN = r"^https://www\.ucpress\.edu/(book/|search\.php\?)"
+
+    @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/university_of_chicago_press_books.py

@@ -0,0 +1,25 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""University of Chicago Press Books translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class UniversityOfChicagoPressBooksTranslator(BaseTranslator):
+    """University of Chicago Press Books."""
+
+    LABEL = "University of Chicago Press Books"
+    URL_TARGET_PATTERN = (
+        r"^https?://(www\.)?press\.uchicago\.edu/(ucp/books/|press/search.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/university_of_wisconsin_madison_libraries_catalog.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""University of Wisconsin-Madison Libraries Catalog translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class UniversityOfWisconsinMadisonLibrariesCatalogTranslator(BaseTranslator):
+    """University of Wisconsin-Madison Libraries Catalog."""
+
+    LABEL = "University of Wisconsin-Madison Libraries Catalog"
+    URL_TARGET_PATTERN = r"^https://search\.library\.wisc\.edu/(catalog|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/university_press_scholarship.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""University Press Scholarship translator."""
+
+import re
+from typing import List
+from playwright.async_api import Page
+from ..core.base import BaseTranslator
+
+
+class UniversityPressScholarshipTranslator(BaseTranslator):
+    """University Press Scholarship."""
+
+    LABEL = "University Press Scholarship"
+    URL_TARGET_PATTERN = r"^https?://[^/]+\.universitypressscholarship\.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 []