novel-downloader 1.3.0__py3-none-any.whl → 1.3.2__py3-none-any.whl

novel_downloader/core/factory/parser.py

@@ -14,19 +14,40 @@ from novel_downloader.core.interfaces import ParserProtocol
 from novel_downloader.core.parsers import (
     BiqugeParser,
     CommonParser,
+    EsjzoneParser,
+    QianbiParser,
     QidianBrowserParser,
     QidianSessionParser,
+    SfacgParser,
+    YamiboParser,
 )
 
 ParserBuilder = Callable[[ParserConfig], ParserProtocol]
 
 _site_map: dict[str, dict[str, ParserBuilder]] = {
+    "biquge": {
+        "session": BiqugeParser,
+        "async": BiqugeParser,
+    },
+    "esjzone": {
+        "session": EsjzoneParser,
+        "async": EsjzoneParser,
+    },
+    "qianbi": {
+        "session": QianbiParser,
+        "async": QianbiParser,
+    },
     "qidian": {
         "browser": QidianBrowserParser,
         "session": QidianSessionParser,
     },
-    "biquge": {
-        "session": BiqugeParser,
+    "sfacg": {
+        "session": SfacgParser,
+        "async": SfacgParser,
+    },
+    "yamibo": {
+        "session": YamiboParser,
+        "async": YamiboParser,
     },
 }
 

novel_downloader/core/factory/requester.py

@@ -15,30 +15,55 @@ from novel_downloader.core.interfaces import (
     SyncRequesterProtocol,
 )
 from novel_downloader.core.requesters import (
+    BiqugeAsyncSession,
     BiqugeSession,
     CommonAsyncSession,
     CommonSession,
+    EsjzoneAsyncSession,
+    EsjzoneSession,
+    QianbiAsyncSession,
+    QianbiSession,
     QidianBrowser,
     QidianSession,
+    SfacgAsyncSession,
+    SfacgSession,
+    YamiboAsyncSession,
+    YamiboSession,
 )
 
 AsyncRequesterBuilder = Callable[[RequesterConfig], AsyncRequesterProtocol]
 SyncRequesterBuilder = Callable[[RequesterConfig], SyncRequesterProtocol]
 
 
-# _async_site_map: dict[str, AsyncRequesterBuilder] = {
-#     # "biquge": ...
-# }
+_async_site_map: dict[str, AsyncRequesterBuilder] = {
+    "biquge": BiqugeAsyncSession,
+    "esjzone": EsjzoneAsyncSession,
+    "qianbi": QianbiAsyncSession,
+    "sfacg": SfacgAsyncSession,
+    "yamibo": YamiboAsyncSession,
+}
 _sync_site_map: dict[
     str,
     dict[str, SyncRequesterBuilder],
 ] = {
+    "biquge": {
+        "session": BiqugeSession,
+    },
+    "esjzone": {
+        "session": EsjzoneSession,
+    },
+    "qianbi": {
+        "session": QianbiSession,
+    },
     "qidian": {
         "session": QidianSession,
         "browser": QidianBrowser,
     },
-    "biquge": {
-        "session": BiqugeSession,
+    "sfacg": {
+        "session": SfacgSession,
+    },
+    "yamibo": {
+        "session": YamiboSession,
     },
 }
 
@@ -57,8 +82,8 @@ def get_async_requester(
     site_key = site.lower()
 
     # site-specific
-    # if site_key in _async_site_map:
-    #     return _async_site_map[site_key](config)
+    if site_key in _async_site_map:
+        return _async_site_map[site_key](config)
 
     # fallback
     site_rules = load_site_rules()

novel_downloader/core/factory/saver.py

@@ -7,17 +7,29 @@ This module implements a factory function for creating saver instances
 based on the site name and parser mode specified in the configuration.
 """
 
+from collections.abc import Callable
+
 from novel_downloader.config import SaverConfig, load_site_rules
 from novel_downloader.core.interfaces import SaverProtocol
 from novel_downloader.core.savers import (
     BiqugeSaver,
     CommonSaver,
+    EsjzoneSaver,
+    QianbiSaver,
     QidianSaver,
+    SfacgSaver,
+    YamiboSaver,
 )
 
-_site_map = {
-    "qidian": QidianSaver,
+SaverBuilder = Callable[[SaverConfig], SaverProtocol]
+
+_site_map: dict[str, SaverBuilder] = {
     "biquge": BiqugeSaver,
+    "esjzone": EsjzoneSaver,
+    "qianbi": QianbiSaver,
+    "qidian": QidianSaver,
+    "sfacg": SfacgSaver,
+    "yamibo": YamiboSaver,
 }
 
 

novel_downloader/core/interfaces/async_requester.py

@@ -40,7 +40,7 @@ class AsyncRequesterProtocol(Protocol):
         self,
         book_id: str,
         **kwargs: Any,
-    ) -> str:
+    ) -> list[str]:
         """
         Fetch the raw HTML (or JSON) of the book info page asynchronously.
 
@@ -54,7 +54,7 @@ class AsyncRequesterProtocol(Protocol):
         book_id: str,
         chapter_id: str,
         **kwargs: Any,
-    ) -> str:
+    ) -> list[str]:
         """
         Fetch the raw HTML (or JSON) of a single chapter asynchronously.
 
@@ -68,7 +68,7 @@ class AsyncRequesterProtocol(Protocol):
         self,
         page: int = 1,
         **kwargs: Any,
-    ) -> str:
+    ) -> list[str]:
         """
         Optional: Retrieve the HTML content of the authenticated
         user's bookcase page asynchronously.

novel_downloader/core/interfaces/parser.py

@@ -21,7 +21,11 @@ class ParserProtocol(Protocol):
       - accept a book_id context for multi-step workflows.
     """
 
-    def parse_book_info(self, html_str: str) -> dict[str, Any]:
+    def parse_book_info(
+        self,
+        html_str: list[str],
+        **kwargs: Any,
+    ) -> dict[str, Any]:
         """
         Parse and return a dictionary of book information from the raw HTML.
 
@@ -32,8 +36,9 @@ class ParserProtocol(Protocol):
 
     def parse_chapter(
         self,
-        html_str: str,
+        html_str: list[str],
         chapter_id: str,
+        **kwargs: Any,
     ) -> ChapterDict | None:
         """
         Parse and return the text content of one chapter.

novel_downloader/core/interfaces/sync_requester.py

@@ -38,7 +38,7 @@ class SyncRequesterProtocol(Protocol):
         self,
         book_id: str,
         **kwargs: Any,
-    ) -> str:
+    ) -> list[str]:
         """
         Fetch the raw HTML (or JSON) of the book info page.
 
@@ -52,7 +52,7 @@ class SyncRequesterProtocol(Protocol):
         book_id: str,
         chapter_id: str,
         **kwargs: Any,
-    ) -> str:
+    ) -> list[str]:
         """
         Fetch the raw HTML (or JSON) of a single chapter.
 
@@ -66,7 +66,7 @@ class SyncRequesterProtocol(Protocol):
         self,
         page: int = 1,
         **kwargs: Any,
-    ) -> str:
+    ) -> list[str]:
         """
         Optional: Retrieve the HTML content of the authenticated user's bookcase page.
 

novel_downloader/core/parsers/__init__.py

@@ -6,24 +6,34 @@ novel_downloader.core.parsers
 This package defines all site-specific parsing modules
 for the novel_downloader framework.
 
-Currently supported:
-- Qidian (起点中文网)
-
 Modules:
-- qidian_parser
-- common_parser
+- biquge (笔趣阁)
+- esjzone (ESJ Zone)
+- qianbi (铅笔小说)
+- qidian (起点中文网)
+- sfacg (SF轻小说)
+- yamibo (百合会)
+- common (通用架构)
 """
 
 from .biquge import BiqugeParser
 from .common import CommonParser
+from .esjzone import EsjzoneParser
+from .qianbi import QianbiParser
 from .qidian import (
     QidianBrowserParser,
     QidianSessionParser,
 )
+from .sfacg import SfacgParser
+from .yamibo import YamiboParser
 
 __all__ = [
     "BiqugeParser",
     "CommonParser",
+    "EsjzoneParser",
+    "QianbiParser",
     "QidianBrowserParser",
     "QidianSessionParser",
+    "SfacgParser",
+    "YamiboParser",
 ]

novel_downloader/core/parsers/base.py

@@ -49,7 +49,11 @@ class BaseParser(ParserProtocol, abc.ABC):
         self._cache_dir = self._base_cache_dir
 
     @abc.abstractmethod
-    def parse_book_info(self, html_str: str) -> dict[str, Any]:
+    def parse_book_info(
+        self,
+        html_str: list[str],
+        **kwargs: Any,
+    ) -> dict[str, Any]:
         """
         Parse a book info page and extract metadata and chapter structure.
 
@@ -64,8 +68,9 @@ class BaseParser(ParserProtocol, abc.ABC):
     @abc.abstractmethod
     def parse_chapter(
         self,
-        html_str: str,
+        html_str: list[str],
         chapter_id: str,
+        **kwargs: Any,
     ) -> ChapterDict | None:
         """
         Parse a single chapter page and extract clean text or simplified HTML.

novel_downloader/core/parsers/biquge/main_parser.py

@@ -18,14 +18,20 @@ from novel_downloader.utils.chapter_storage import ChapterDict
 class BiqugeParser(BaseParser):
     """ """
 
-    def parse_book_info(self, html_str: str) -> dict[str, Any]:
+    def parse_book_info(
+        self,
+        html_str: list[str],
+        **kwargs: Any,
+    ) -> dict[str, Any]:
         """
         Parse a book info page and extract metadata and chapter structure.
 
         :param html: Raw HTML of the book info page.
         :return: Parsed metadata and chapter structure as a dictionary.
         """
-        tree = etree.HTML(html_str, parser=None)
+        if not html_str:
+            return {}
+        tree = etree.HTML(html_str[0])
         result: dict[str, Any] = {}
 
         def extract_text(elem: _Element | None) -> str:
@@ -90,8 +96,9 @@ class BiqugeParser(BaseParser):
 
     def parse_chapter(
         self,
-        html_str: str,
+        html_str: list[str],
         chapter_id: str,
+        **kwargs: Any,
     ) -> ChapterDict | None:
         """
         Parse a single chapter page and extract clean text or simplified HTML.
@@ -100,7 +107,9 @@ class BiqugeParser(BaseParser):
         :param chapter_id: Identifier of the chapter being parsed.
         :return: Cleaned chapter content as plain text or minimal HTML.
         """
-        tree = etree.HTML(html_str, parser=None)
+        if not html_str:
+            return None
+        tree = etree.HTML(html_str[0], parser=None)
 
         # 提取标题
         title_elem = tree.xpath('//div[@class="bookname"]/h1')

novel_downloader/core/parsers/common/main_parser.py

@@ -35,21 +35,28 @@ class CommonParser(BaseParser):
         self._site = site
         self._site_rule = site_rule
 
-    def parse_book_info(self, html_str: str) -> dict[str, Any]:
+    def parse_book_info(
+        self,
+        html_str: list[str],
+        **kwargs: Any,
+    ) -> dict[str, Any]:
         """
         Parse a book info page and extract metadata and chapter structure.
 
         :param html: Raw HTML of the book info page.
         :return: Parsed metadata and chapter structure as a dictionary.
         """
-        extractor = HTMLExtractor(html_str)
+        if not html_str:
+            return {}
+        extractor = HTMLExtractor(html_str[0])
         rules = self._site_rule["book_info"]
         return extractor.extract_book_info(rules)
 
     def parse_chapter(
         self,
-        html_str: str,
+        html_str: list[str],
         chapter_id: str,
+        **kwargs: Any,
     ) -> ChapterDict | None:
         """
         Parse a single chapter page and extract clean text or simplified HTML.
@@ -58,7 +65,9 @@ class CommonParser(BaseParser):
         :param chapter_id: Identifier of the chapter being parsed.
         :return: Cleaned chapter content as plain text or minimal HTML.
         """
-        extractor = HTMLExtractor(html_str)
+        if not html_str:
+            return None
+        extractor = HTMLExtractor(html_str[0])
         chapter_rules = self._site_rule["chapter"]
 
         # 必须有正文内容

novel_downloader/core/parsers/esjzone/__init__.py

@@ -0,0 +1,10 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.parsers.esjzone
+-------------------------------------
+
+"""
+
+from .main_parser import EsjzoneParser
+
+__all__ = ["EsjzoneParser"]

novel_downloader/core/parsers/esjzone/main_parser.py

@@ -0,0 +1,219 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.parsers.esjzone.main_parser
+-------------------------------------------------
+
+"""
+
+from typing import Any
+
+from lxml import etree
+from lxml.etree import _Element
+
+from novel_downloader.core.parsers.base import BaseParser
+from novel_downloader.utils.chapter_storage import ChapterDict
+
+
+class EsjzoneParser(BaseParser):
+    """ """
+
+    # Book info XPaths
+    _BOOK_NAME_XPATH = '//h2[contains(@class, "text-normal")]/text()'
+    _AUTHOR_XPATH = '//li[strong[text()="作者:"]]/a/text()'
+    _COVER_URL_XPATH = '//div[contains(@class,"product-gallery")]//img/@src'
+    _UPDATE_TIME_XPATH = '//li[strong[text()="更新日期:"]]/text()'
+    _WORD_COUNT_XPATH = '//span[@id="txt"]/text()'
+    _TYPE_XPATH = '//li[strong[text()="類型:"]]/text()'
+    _ALT_NAME_XPATH = '//li[strong[text()="其他書名:"]]/text()'
+    _WEB_URL_XPATH = '//li[strong[text()="Web生肉:"]]/a/@href'
+    _SUMMARY_XPATH = '//div[@class="description"]/p//text()'
+
+    # Chapter XPaths
+    _CHAPTER_TEXT_XPATH = 'string(//div[contains(@class, "forum-content")])'
+    _CHAPTER_CONTENT_NODES_XPATH = '//div[contains(@class, "forum-content")]/*'
+    _CHAPTER_TIME_XPATHS = [
+        '//i[contains(@class, "icon-clock")]/following-sibling::text()',
+        '//i[contains(@class, "icon-pen-tool")]/following-sibling::text()',
+    ]
+
+    _CHECK_FORUM_XPATH = '//div[@class="page-title"]//ul[@class="breadcrumbs"]/li[not(@class="slash")]//text()'  # noqa: E501
+
+    def parse_book_info(
+        self,
+        html_str: list[str],
+        **kwargs: Any,
+    ) -> dict[str, Any]:
+        """
+        Parse a book info page and extract metadata and chapter structure.
+
+        注: 由于网站使用了多种不同的分卷格式, 已经尝试兼容常见情况,
+        但仍可能存在未覆盖的 cases
+
+        :param html: Raw HTML of the book info page.
+        :return: Parsed metadata and chapter structure as a dictionary.
+        """
+        if not html_str or self._is_forum_page(html_str):
+            return {}
+        tree = etree.HTML(html_str[0])
+        result: dict[str, Any] = {}
+
+        result["book_name"] = self._get_text(tree, self._BOOK_NAME_XPATH)
+        result["author"] = self._get_text(tree, self._AUTHOR_XPATH)
+        result["cover_url"] = self._get_text(tree, self._COVER_URL_XPATH)
+        result["update_time"] = self._get_text(tree, self._UPDATE_TIME_XPATH)
+        result["word_count"] = self._get_text(
+            tree, self._WORD_COUNT_XPATH, clean_comma=True
+        )
+        result["type"] = self._get_text(tree, self._TYPE_XPATH)
+        result["alt_name"] = self._get_text(tree, self._ALT_NAME_XPATH)
+        result["web_url"] = self._get_text(tree, self._WEB_URL_XPATH)
+        # result["summary"] = self._get_text(tree, self._SUMMARY_XPATH, join=True)
+        paras = tree.xpath('//div[@class="description"]/p')
+        texts = [p.xpath("string()").strip() for p in paras]
+        result["summary"] = "\n".join(texts).strip()
+
+        volumes: list[dict[str, Any]] = []
+        current_vol: dict[str, Any] = {}
+
+        def _start_volume(name: str) -> None:
+            nonlocal current_vol
+            name = name.strip() or "未命名卷"
+            if name == "未命名卷" and current_vol is not None:
+                return
+            current_vol = {"volume_name": name, "chapters": []}
+            volumes.append(current_vol)
+
+        _start_volume("單卷")
+
+        nodes = tree.xpath('//div[@id="chapterList"]/details') + tree.xpath(
+            '//div[@id="chapterList"]/*[not(self::details)]'
+        )
+
+        for node in nodes:
+            tag = node.tag.lower()
+
+            if tag == "details":
+                # ---- DETAILS‐based layout ----
+                summary = node.find("summary")
+                vol_name = summary.text if summary is not None else "未命名卷"
+                _start_volume(vol_name)
+
+                # all chapters inside this details
+                for a in node.findall("a"):
+                    title = "".join(a.xpath(".//p//text()")).strip()
+                    href = a.get("href", "")
+                    chap_id = href.rstrip("/").split("/")[-1].split(".", 1)[0]
+                    current_vol["chapters"].append(
+                        {"title": title, "url": href, "chapterId": chap_id}
+                    )
+
+            elif (
+                tag in ("h2",)
+                or (tag == "p" and node.get("class") == "non")
+                or tag == "summary"
+            ):
+                # Handle possible volume title markers:
+                # - <h2>: standard volume header
+                # - <p class="non">: alternative volume header style
+                # - <summary>: fallback for stray <summary> tags outside <details>
+                _start_volume(node.xpath("string()"))
+
+            elif tag == "a":
+                # ---- chapter link, attach to current volume ----
+                title = "".join(node.xpath(".//p//text()")).strip()
+                href = node.get("href", "")
+                chap_id = href.rstrip("/").split("/")[-1].split(".", 1)[0]
+                current_vol["chapters"].append(
+                    {"title": title, "url": href, "chapterId": chap_id}
+                )
+        volumes = [vol for vol in volumes if vol["chapters"]]
+        result["volumes"] = volumes
+
+        return result
+
+    def parse_chapter(
+        self,
+        html_str: list[str],
+        chapter_id: str,
+        **kwargs: Any,
+    ) -> ChapterDict | None:
+        """
+        Parse a single chapter page and extract clean text or simplified HTML.
+
+        :param html: Raw HTML of the chapter page.
+        :param chapter_id: Identifier of the chapter being parsed.
+        :return: Cleaned chapter content as plain text or minimal HTML.
+        """
+        if not html_str or self._is_forum_page(html_str):
+            return None
+        tree = etree.HTML(html_str[0], parser=None)
+
+        content_lines: list[str] = []
+        content_nodes = tree.xpath(self._CHAPTER_CONTENT_NODES_XPATH)
+        for node in content_nodes:
+            if node.tag == "p":
+                img_srcs = node.xpath(".//img/@src")
+                if img_srcs:
+                    for src in img_srcs:
+                        content_lines.append(f'<img src="{src}" />')
+                else:
+                    text = "".join(node.xpath(".//text()")).strip()
+                    if text:
+                        content_lines.append(text)
+            elif node.tag == "a":
+                img_srcs = node.xpath(".//img/@src")
+                for src in img_srcs:
+                    content_lines.append(f'<img src="{src}" />')
+
+        content = (
+            "\n\n".join(content_lines).strip()
+            if content_lines
+            else tree.xpath(self._CHAPTER_TEXT_XPATH).strip()
+        )
+        if not content:
+            return None
+
+        title_nodes = tree.xpath("//h2/text()")
+        title = title_nodes[0].strip() if title_nodes else ""
+
+        updated_at = next(
+            (
+                x.strip()
+                for xp in self._CHAPTER_TIME_XPATHS
+                for x in tree.xpath(xp)
+                if x.strip()
+            ),
+            "",
+        )
+
+        return {
+            "id": chapter_id,
+            "title": title,
+            "content": content,
+            "extra": {"site": "esjzone", "updated_at": updated_at},
+        }
+
+    def _is_forum_page(self, html_str: list[str]) -> bool:
+        if not html_str:
+            return False
+
+        tree = etree.HTML(html_str[0])
+        page_title = tree.xpath('string(//div[@class="page-title"]//h1)').strip()
+        if page_title != "論壇":
+            return False
+        breadcrumb: list[str] = tree.xpath(self._CHECK_FORUM_XPATH)
+        breadcrumb = [s.strip() for s in breadcrumb if s.strip()]
+        return breadcrumb == ["Home", "論壇"]
+
+    @staticmethod
+    def _get_text(
+        tree: _Element,
+        xpath: str,
+        join: bool = False,
+        clean_comma: bool = False,
+    ) -> str:
+        data = tree.xpath(xpath)
+        if not data:
+            return ""
+        text = "\n".join(data) if join else data[0].strip()
+        return text.replace(",", "") if clean_comma else text

novel_downloader/core/parsers/qianbi/__init__.py

@@ -0,0 +1,10 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.parsers.qianbi
+------------------------------------
+
+"""
+
+from .main_parser import QianbiParser
+
+__all__ = ["QianbiParser"]