novel-downloader 1.3.1__py3-none-any.whl → 1.3.3__py3-none-any.whl

novel_downloader/core/requesters/esjzone/session.py

@@ -0,0 +1,235 @@
+"""
+novel_downloader.core.requesters.esjzone.session
+----------------------------------------------
+
+"""
+
+import re
+from typing import Any
+
+from novel_downloader.config.models import RequesterConfig
+from novel_downloader.core.requesters.base import BaseSession
+from novel_downloader.utils.i18n import t
+from novel_downloader.utils.state import state_mgr
+from novel_downloader.utils.time_utils import sleep_with_random_delay
+
+
+class EsjzoneSession(BaseSession):
+    """
+    A session class for interacting with the
+    esjzone (www.esjzone.cc) novel website.
+    """
+
+    BOOKCASE_URL = "https://www.esjzone.cc/my/favorite"
+    BOOK_INFO_URL = "https://www.esjzone.cc/detail/{book_id}.html"
+    CHAPTER_URL = "https://www.esjzone.cc/forum/{book_id}/{chapter_id}.html"
+
+    API_LOGIN_URL_1 = "https://www.esjzone.cc/my/login"
+    API_LOGIN_URL_2 = "https://www.esjzone.cc/inc/mem_login.php"
+
+    def __init__(
+        self,
+        config: RequesterConfig,
+    ):
+        super().__init__(config)
+        self._logged_in: bool = False
+        self._request_interval = config.backoff_factor
+        self._retry_times = config.retry_times
+        self._username = config.username
+        self._password = config.password
+
+    def login(
+        self,
+        username: str = "",
+        password: str = "",
+        manual_login: bool = False,
+        **kwargs: Any,
+    ) -> bool:
+        """
+        Restore cookies persisted by the session-based workflow.
+        """
+        cookies: dict[str, str] = state_mgr.get_cookies("esjzone")
+        username = username or self._username
+        password = password or self._password
+
+        self.update_cookies(cookies)
+        for _ in range(self._retry_times):
+            if self._check_login_status():
+                self.logger.debug("[auth] Already logged in.")
+                self._logged_in = True
+                return True
+            if username and password and not self._api_login(username, password):
+                print(t("session_login_failed", site="esjzone"))
+            sleep_with_random_delay(
+                self._request_interval,
+                mul_spread=1.1,
+                max_sleep=self._request_interval + 2,
+            )
+
+        self._logged_in = self._check_login_status()
+        return self._logged_in
+
+    def get_book_info(
+        self,
+        book_id: str,
+        **kwargs: Any,
+    ) -> list[str]:
+        """
+        Fetch the raw HTML of the book info and catalog pages.
+
+        Order: [info, catalog]
+
+        :param book_id: The book identifier.
+        :return: The page content as a string.
+        """
+        url = self.book_info_url(book_id=book_id)
+        try:
+            resp = self.get(url, **kwargs)
+            resp.raise_for_status()
+            return [resp.text]
+        except Exception as exc:
+            self.logger.warning(
+                "[session] get_book_info(%s) failed: %s",
+                book_id,
+                exc,
+            )
+        return []
+
+    def get_book_chapter(
+        self,
+        book_id: str,
+        chapter_id: str,
+        **kwargs: Any,
+    ) -> list[str]:
+        """
+        Fetch the HTML of a single chapter.
+
+        :param book_id: The book identifier.
+        :param chapter_id: The chapter identifier.
+        :return: The chapter content as a string.
+        """
+        url = self.chapter_url(book_id=book_id, chapter_id=chapter_id)
+        try:
+            resp = self.get(url, **kwargs)
+            resp.raise_for_status()
+            return [resp.text]
+        except Exception as exc:
+            self.logger.warning(
+                "[session] get_book_chapter(%s) failed: %s",
+                book_id,
+                exc,
+            )
+        return []
+
+    def get_bookcase(
+        self,
+        page: int = 1,
+        **kwargs: Any,
+    ) -> list[str]:
+        """
+        Retrieve the user's *bookcase* page.
+
+        :return: The HTML markup of the bookcase page.
+        """
+        url = self.bookcase_url()
+        try:
+            resp = self.get(url, **kwargs)
+            resp.raise_for_status()
+            return [resp.text]
+        except Exception as exc:
+            self.logger.warning(
+                "[session] get_bookcase failed: %s",
+                exc,
+            )
+        return []
+
+    @classmethod
+    def bookcase_url(cls) -> str:
+        """
+        Construct the URL for the user's bookcase page.
+
+        :return: Fully qualified URL of the bookcase.
+        """
+        return cls.BOOKCASE_URL
+
+    @classmethod
+    def book_info_url(cls, book_id: str) -> str:
+        """
+        Construct the URL for fetching a book's info page.
+
+        :param book_id: The identifier of the book.
+        :return: Fully qualified URL for the book info page.
+        """
+        return cls.BOOK_INFO_URL.format(book_id=book_id)
+
+    @classmethod
+    def chapter_url(cls, book_id: str, chapter_id: str) -> str:
+        """
+        Construct the URL for fetching a specific chapter.
+
+        :param book_id: The identifier of the book.
+        :param chapter_id: The identifier of the chapter.
+        :return: Fully qualified chapter URL.
+        """
+        return cls.CHAPTER_URL.format(book_id=book_id, chapter_id=chapter_id)
+
+    def _api_login(self, username: str, password: str) -> bool:
+        """
+        Login to the API using a 2-step token-based process.
+
+        Step 1: Get auth token.
+        Step 2: Use token and credentials to perform login.
+        Return True if login succeeds, False otherwise.
+        """
+        data_1 = {
+            "plxf": "getAuthToken",
+        }
+        try:
+            resp_1 = self.post(self.API_LOGIN_URL_1, data=data_1)
+            resp_1.raise_for_status()
+            # Example response: <JinJing>token_here</JinJing>
+            token = self._extract_token(resp_1.text)
+        except Exception as exc:
+            self.logger.warning("[session] _api_login failed at step 1: %s", exc)
+            return False
+
+        data_2 = {
+            "email": username,
+            "pwd": password,
+            "remember_me": "on",
+        }
+        temp_headers = dict(self.headers)
+        temp_headers["Authorization"] = token
+        try:
+            resp_2 = self.post(self.API_LOGIN_URL_2, data=data_2, headers=temp_headers)
+            resp_2.raise_for_status()
+            resp_code: int = resp_2.json().get("status", 301)
+            return resp_code == 200
+        except Exception as exc:
+            self.logger.warning("[session] _api_login failed at step 2: %s", exc)
+        return False
+
+    def _check_login_status(self) -> bool:
+        """
+        Check whether the user is currently logged in by
+        inspecting the bookcase page content.
+
+        :return: True if the user is logged in, False otherwise.
+        """
+        keywords = [
+            "window.location.href='/my/login'",
+        ]
+        resp_text = self.get_bookcase()
+        if not resp_text:
+            return False
+        return not any(kw in resp_text[0] for kw in keywords)
+
+    def _extract_token(self, text: str) -> str:
+        match = re.search(r"<JinJing>(.+?)</JinJing>", text)
+        return match.group(1) if match else ""
+
+    def _on_close(self) -> None:
+        """
+        Save cookies to the state manager before closing.
+        """
+        state_mgr.set_cookies("esjzone", self.cookies)

novel_downloader/core/requesters/qianbi/__init__.py

@@ -0,0 +1,13 @@
+"""
+novel_downloader.core.requesters.qianbi
+---------------------------------------
+
+"""
+
+from .async_session import QianbiAsyncSession
+from .session import QianbiSession
+
+__all__ = [
+    "QianbiAsyncSession",
+    "QianbiSession",
+]

novel_downloader/core/requesters/qianbi/async_session.py

@@ -0,0 +1,96 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.requesters.qianbi.async_session
+-----------------------------------------------------
+
+"""
+
+import asyncio
+from typing import Any
+
+from novel_downloader.core.requesters.base import BaseAsyncSession
+
+
+class QianbiAsyncSession(BaseAsyncSession):
+    """
+    A async session class for interacting with the
+    Qianbi (www.23qb.com) novel website.
+    """
+
+    BASE_URLS = [
+        "www.23qb.com",
+        "www.23qb.net",
+    ]
+
+    BOOK_INFO_URL = "https://www.23qb.com/book/{book_id}/"
+    BOOK_CATALOG_URL = "https://www.23qb.com/book/{book_id}/catalog"
+    CHAPTER_URL = "https://www.23qb.com/book/{book_id}/{chapter_id}.html"
+
+    async def get_book_info(
+        self,
+        book_id: str,
+        **kwargs: Any,
+    ) -> list[str]:
+        """
+        Fetch the raw HTML of the book info page asynchronously.
+
+        Order: [info, catalog]
+
+        :param book_id: The book identifier.
+        :return: The page content as a string.
+        """
+        info_url = self.book_info_url(book_id=book_id)
+        catalog_url = self.book_catalog_url(book_id=book_id)
+
+        info_html, catalog_html = await asyncio.gather(
+            self.fetch(info_url, **kwargs),
+            self.fetch(catalog_url, **kwargs),
+        )
+        return [info_html, catalog_html]
+
+    async def get_book_chapter(
+        self,
+        book_id: str,
+        chapter_id: str,
+        **kwargs: Any,
+    ) -> list[str]:
+        """
+        Fetch the raw HTML of a single chapter asynchronously.
+
+        :param book_id: The book identifier.
+        :param chapter_id: The chapter identifier.
+        :return: The chapter content as a string.
+        """
+        url = self.chapter_url(book_id=book_id, chapter_id=chapter_id)
+        return [await self.fetch(url, **kwargs)]
+
+    @classmethod
+    def book_info_url(cls, book_id: str) -> str:
+        """
+        Construct the URL for fetching a book's info page.
+
+        :param book_id: The identifier of the book.
+        :return: Fully qualified URL for the book info page.
+        """
+        return cls.BOOK_INFO_URL.format(book_id=book_id)
+
+    @classmethod
+    def book_catalog_url(cls, book_id: str) -> str:
+        """
+        Construct the URL for fetching a book's catalog page.
+
+        :param book_id: The identifier of the book.
+        :return: Fully qualified catalog page URL.
+        """
+        return cls.BOOK_CATALOG_URL.format(book_id=book_id)
+
+    @classmethod
+    def chapter_url(cls, book_id: str, chapter_id: str) -> str:
+        """
+        Construct the URL for fetching a specific chapter.
+
+        :param book_id: The identifier of the book.
+        :param chapter_id: The identifier of the chapter.
+        :return: Fully qualified chapter URL.
+        """
+        return cls.CHAPTER_URL.format(book_id=book_id, chapter_id=chapter_id)

novel_downloader/core/requesters/qianbi/session.py

@@ -0,0 +1,125 @@
+"""
+novel_downloader.core.requesters.qianbi.session
+-----------------------------------------------
+
+"""
+
+from typing import Any
+
+from novel_downloader.core.requesters.base import BaseSession
+
+
+class QianbiSession(BaseSession):
+    """
+    A session class for interacting with the
+    Qianbi (www.23qb.com) novel website.
+    """
+
+    BASE_URLS = [
+        "www.23qb.com",
+        "www.23qb.net",
+    ]
+
+    BOOK_INFO_URL = "https://www.23qb.com/book/{book_id}/"
+    BOOK_CATALOG_URL = "https://www.23qb.com/book/{book_id}/catalog"
+    CHAPTER_URL = "https://www.23qb.com/book/{book_id}/{chapter_id}.html"
+
+    def get_book_info(
+        self,
+        book_id: str,
+        **kwargs: Any,
+    ) -> list[str]:
+        """
+        Fetch the raw HTML of the book info and catalog pages.
+
+        Order: [info, catalog]
+
+        :param book_id: The book identifier.
+        :return: The page content as a string.
+        """
+        info_url = self.book_info_url(book_id=book_id)
+        catalog_url = self.book_catalog_url(book_id=book_id)
+
+        pages = []
+        try:
+            resp = self.get(info_url, **kwargs)
+            resp.raise_for_status()
+            pages.append(resp.text)
+        except Exception as exc:
+            self.logger.warning(
+                "[session] get_book_info(info:%s) failed: %s",
+                book_id,
+                exc,
+            )
+            pages.append("")
+
+        try:
+            resp = self.get(catalog_url, **kwargs)
+            resp.raise_for_status()
+            pages.append(resp.text)
+        except Exception as exc:
+            self.logger.warning(
+                "[session] get_book_info(catalog:%s) failed: %s",
+                book_id,
+                exc,
+            )
+            pages.append("")
+
+        return pages
+
+    def get_book_chapter(
+        self,
+        book_id: str,
+        chapter_id: str,
+        **kwargs: Any,
+    ) -> list[str]:
+        """
+        Fetch the HTML of a single chapter.
+
+        :param book_id: The book identifier.
+        :param chapter_id: The chapter identifier.
+        :return: The chapter content as a string.
+        """
+        url = self.chapter_url(book_id=book_id, chapter_id=chapter_id)
+        try:
+            resp = self.get(url, **kwargs)
+            resp.raise_for_status()
+            return [resp.text]
+        except Exception as exc:
+            self.logger.warning(
+                "[session] get_book_chapter(%s) failed: %s",
+                book_id,
+                exc,
+            )
+        return []
+
+    @classmethod
+    def book_info_url(cls, book_id: str) -> str:
+        """
+        Construct the URL for fetching a book's info page.
+
+        :param book_id: The identifier of the book.
+        :return: Fully qualified URL for the book info page.
+        """
+        return cls.BOOK_INFO_URL.format(book_id=book_id)
+
+    @classmethod
+    def book_catalog_url(cls, book_id: str) -> str:
+        """
+        Construct the URL for fetching a book's catalog page.
+
+        :param book_id: The identifier of the book.
+        :return: Fully qualified catalog page URL.
+        """
+        return cls.BOOK_CATALOG_URL.format(book_id=book_id)
+
+    @classmethod
+    def chapter_url(cls, book_id: str, chapter_id: str) -> str:
+        """
+        Construct the URL for fetching a specific chapter.
+
+        :param book_id: The identifier of the book.
+        :param chapter_id: The identifier of the chapter.
+        :return: Fully qualified chapter URL.
+        """
+        return cls.CHAPTER_URL.format(book_id=book_id, chapter_id=chapter_id)

novel_downloader/core/requesters/qidian/broswer.py

@@ -63,7 +63,7 @@ class QidianBrowser(BaseBrowser):
         self,
         book_id: str,
         **kwargs: Any,
-    ) -> str:
+    ) -> list[str]:
         """
         Retrieve the HTML of a Qidian book info page.
 
@@ -78,19 +78,19 @@ class QidianBrowser(BaseBrowser):
             self.logger.debug(
                 "[fetch] Fetched book info for ID %s from %s", book_id, url
             )
-            return html
+            return [html]
         except Exception as e:
             self.logger.warning(
                 "[fetch] Error fetching book info from '%s': %s", url, e
             )
-        return ""
+        return []
 
     def get_book_chapter(
         self,
         book_id: str,
         chapter_id: str,
         **kwargs: Any,
-    ) -> str:
+    ) -> list[str]:
         """
         Retrieve the HTML content of a specific chapter.
 
@@ -108,16 +108,16 @@ class QidianBrowser(BaseBrowser):
             self.logger.debug(
                 "[fetch] Fetched chapter %s for book %s", chapter_id, book_id
             )
-            return html
+            return [html]
         except Exception as e:
             self.logger.warning("[fetch] Error fetching chapter from '%s': %s", url, e)
-        return ""
+        return []
 
     def get_bookcase(
         self,
         page: int = 1,
         **kwargs: Any,
-    ) -> str:
+    ) -> list[str]:
         """
         Retrieve the HTML content of the logged-in user's Qidian bookcase page.
 
@@ -133,10 +133,10 @@ class QidianBrowser(BaseBrowser):
             self.page.get(url)
             html = str(self.page.html)
             self.logger.debug("[fetch] Fetched bookcase HTML from %s", url)
-            return html
+            return [html]
         except Exception as e:
             self.logger.warning("[fetch] Error fetching bookcase from '%s': %s", url, e)
-        return ""
+        return []
 
     @classmethod
     def book_info_url(cls, book_id: str) -> str:

novel_downloader/core/requesters/qidian/session.py

@@ -67,7 +67,7 @@ class QidianSession(BaseSession):
         **kwargs: Any,
     ) -> bool:
         """
-        Restore cookies persisted by the browser-based workflow.
+        Restore cookies persisted by the session-based workflow.
         """
         cookies: dict[str, str] = state_mgr.get_cookies("qidian")
 
@@ -76,6 +76,7 @@ class QidianSession(BaseSession):
         for attempt in range(1, self._retry_times + 1):
             if self._check_login_status():
                 self.logger.debug("[auth] Already logged in.")
+                self._logged_in = True
                 return True
 
             if attempt == 1:
@@ -100,7 +101,7 @@ class QidianSession(BaseSession):
         self,
         book_id: str,
         **kwargs: Any,
-    ) -> str:
+    ) -> list[str]:
         """
         Fetch the raw HTML of the book info page.
 
@@ -111,21 +112,21 @@ class QidianSession(BaseSession):
         try:
             resp = self.get(url, **kwargs)
             resp.raise_for_status()
-            return resp.text
+            return [resp.text]
         except Exception as exc:
             self.logger.warning(
                 "[session] get_book_info(%s) failed: %s",
                 book_id,
                 exc,
             )
-        return ""
+        return []
 
     def get_book_chapter(
         self,
         book_id: str,
         chapter_id: str,
         **kwargs: Any,
-    ) -> str:
+    ) -> list[str]:
         """
         Fetch the HTML of a single chapter.
 
@@ -137,20 +138,20 @@ class QidianSession(BaseSession):
         try:
             resp = self.get(url, **kwargs)
             resp.raise_for_status()
-            return resp.text
+            return [resp.text]
         except Exception as exc:
             self.logger.warning(
                 "[session] get_book_chapter(%s) failed: %s",
                 book_id,
                 exc,
             )
-        return ""
+        return []
 
     def get_bookcase(
         self,
         page: int = 1,
         **kwargs: Any,
-    ) -> str:
+    ) -> list[str]:
         """
         Retrieve the user's *bookcase* page.
 
@@ -160,13 +161,13 @@ class QidianSession(BaseSession):
         try:
             resp = self.get(url, **kwargs)
             resp.raise_for_status()
-            return resp.text
+            return [resp.text]
         except Exception as exc:
             self.logger.warning(
                 "[session] get_bookcase failed: %s",
                 exc,
             )
-        return ""
+        return []
 
     def get(
         self,
@@ -247,7 +248,9 @@ class QidianSession(BaseSession):
             "C2WF946J0/probe.js",
         ]
         resp_text = self.get_bookcase()
-        return not any(kw in resp_text for kw in keywords)
+        if not resp_text:
+            return False
+        return not any(kw in resp_text[0] for kw in keywords)
 
     @staticmethod
     def _parse_cookie_input(cookie_str: str) -> dict[str, str]:

novel_downloader/core/requesters/sfacg/__init__.py

@@ -0,0 +1,13 @@
+"""
+novel_downloader.core.requesters.sfacg
+--------------------------------------
+
+"""
+
+from .async_session import SfacgAsyncSession
+from .session import SfacgSession
+
+__all__ = [
+    "SfacgAsyncSession",
+    "SfacgSession",
+]