novel-downloader 1.3.1__py3-none-any.whl → 1.3.2__py3-none-any.whl

novel_downloader/core/parsers/qianbi/main_parser.py

@@ -0,0 +1,142 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.parsers.biquge.main_parser
+------------------------------------------------
+
+"""
+
+from datetime import datetime
+from typing import Any
+
+from lxml import etree
+
+from novel_downloader.core.parsers.base import BaseParser
+from novel_downloader.utils.chapter_storage import ChapterDict
+
+
+class QianbiParser(BaseParser):
+    """ """
+
+    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.
+        """
+        if len(html_str) < 2:
+            return {}
+
+        info_tree = etree.HTML(html_str[0])
+        catalog_tree = etree.HTML(html_str[1])
+        result: dict[str, Any] = {}
+
+        title = info_tree.xpath('//h1[@class="page-title"]/text()')
+        result["book_name"] = title[0].strip() if title else ""
+
+        author = info_tree.xpath('//a[contains(@href,"/author/")]/@title')
+        result["author"] = author[0].strip() if author else ""
+
+        cover = info_tree.xpath('//div[@class="novel-cover"]//img/@data-src')
+        result["cover_url"] = cover[0].strip() if cover else ""
+
+        status = info_tree.xpath(
+            '//a[@class="tag-link" and (text()="完结" or text()="连载")]/text()'
+        )
+        result["serial_status"] = status[0] if status else ""
+
+        word_count_raw = info_tree.xpath('//span[contains(text(), "万字")]/text()')
+        result["word_count"] = word_count_raw[0].strip() if word_count_raw else ""
+
+        summary_node = info_tree.xpath(
+            '//div[@class="novel-info-item novel-info-content"]/span'
+        )
+        if summary_node and summary_node[0] is not None:
+            result["summary"] = etree.tostring(
+                summary_node[0], encoding="unicode", method="text"
+            ).strip()
+        else:
+            result["summary"] = ""
+
+        result["update_time"] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+
+        volumes: list[dict[str, Any]] = []
+        current_volume = None
+
+        for elem in catalog_tree.xpath('//div[@class="box"]/*'):
+            class_attr = elem.get("class", "")
+            class_list = class_attr.split()
+
+            if elem.tag == "h2" and "module-title" in class_list:
+                if current_volume:
+                    volumes.append(current_volume)
+                current_volume = {
+                    "volume_name": elem.text.strip() if elem.text else "",
+                    "chapters": [],
+                }
+            elif (
+                elem.tag == "div" and "module-row-info" in class_list and current_volume
+            ):
+                a_tag = elem.xpath('.//a[@class="module-row-text"]')
+                if a_tag:
+                    title = a_tag[0].xpath(".//span/text()")
+                    href = a_tag[0].attrib.get("href", "")
+                    chapter_id = (
+                        href.split("/")[-1].replace(".html", "") if href else ""
+                    )
+                    current_volume["chapters"].append(
+                        {
+                            "title": title[0].strip() if title else "",
+                            "url": href,
+                            "chapterId": chapter_id,
+                        }
+                    )
+
+        if current_volume:
+            volumes.append(current_volume)
+
+        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:
+            return None
+        tree = etree.HTML(html_str[0])
+
+        paras = tree.xpath('//div[@class="article-content"]/p/text()')
+        content_text = "\n\n".join(p.strip() for p in paras if p.strip())
+        if not content_text:
+            return None
+
+        title = tree.xpath('//h1[@class="article-title"]/text()')
+        title_text = title[0].strip() if title else ""
+
+        volume = tree.xpath('//h3[@class="text-muted"]/text()')
+        volume_text = volume[0].strip() if volume else ""
+
+        return {
+            "id": chapter_id,
+            "title": title_text,
+            "content": content_text,
+            "extra": {
+                "site": "qianbi",
+                "volume": volume_text,
+            },
+        }

novel_downloader/core/parsers/qidian/browser/main_parser.py

@@ -69,26 +69,35 @@ class QidianBrowserParser(BaseParser):
             self._font_debug_dir = self._base_cache_dir / "qidian" / "font_debug"
             self._font_debug_dir.mkdir(parents=True, exist_ok=True)
 
-    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_str: Raw HTML of the book info page.
         :return: Parsed metadata and chapter structure as a dictionary.
         """
-        return parse_book_info(html_str)
+        if not html_str:
+            return {}
+        return parse_book_info(html_str[0])
 
     def parse_chapter(
         self,
-        html_str: str,
+        html_str: list[str],
         chapter_id: str,
+        **kwargs: Any,
     ) -> ChapterDict | None:
         """
         :param html: Raw HTML of the chapter page.
         :param chapter_id: Identifier of the chapter being parsed.
         :return: Cleaned chapter content as plain text.
         """
-        return parse_chapter(self, html_str, chapter_id)
+        if not html_str:
+            return None
+        return parse_chapter(self, html_str[0], chapter_id)
 
     def is_encrypted(self, html_str: str) -> bool:
         """

novel_downloader/core/parsers/qidian/session/main_parser.py

@@ -72,26 +72,35 @@ class QidianSessionParser(BaseParser):
             self._font_debug_dir = self._base_cache_dir / "qidian" / "font_debug"
             self._font_debug_dir.mkdir(parents=True, exist_ok=True)
 
-    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_str: Raw HTML of the book info page.
         :return: Parsed metadata and chapter structure as a dictionary.
         """
-        return parse_book_info(html_str)
+        if not html_str:
+            return {}
+        return parse_book_info(html_str[0])
 
     def parse_chapter(
         self,
-        html_str: str,
+        html_str: list[str],
         chapter_id: str,
+        **kwargs: Any,
     ) -> ChapterDict | None:
         """
         :param html: Raw HTML of the chapter page.
         :param chapter_id: Identifier of the chapter being parsed.
         :return: Cleaned chapter content as plain text.
         """
-        return parse_chapter(self, html_str, chapter_id)
+        if not html_str:
+            return None
+        return parse_chapter(self, html_str[0], chapter_id)
 
     def is_encrypted(self, html_str: str) -> bool:
         """

novel_downloader/core/parsers/sfacg/__init__.py

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

novel_downloader/core/parsers/sfacg/main_parser.py

@@ -0,0 +1,166 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.parsers.sfacg.main_parser
+-----------------------------------------------
+
+"""
+
+from typing import Any
+
+from lxml import etree
+
+from novel_downloader.core.parsers.base import BaseParser
+from novel_downloader.utils.chapter_storage import ChapterDict
+
+
+class SfacgParser(BaseParser):
+    """ """
+
+    # Book info XPaths
+    _BOOK_NAME_XPATH = '//ul[@class="book_info"]//span[@class="book_newtitle"]/text()'
+    _AUTHOR_INFO_XPATH = '//ul[@class="book_info"]//span[@class="book_info3"]/text()'
+    _UPDATE_TIME_XPATH = '//ul[@class="book_info"]//span[@class="book_info3"]/br/following-sibling::text()'  # noqa: E501
+    _COVER_URL_XPATH = '//ul[@class="book_info"]//li/img/@src'
+    _STATUS_XPATH = '//ul[@class="book_info"]//div[@class="book_info2"]/span/text()'
+    _SUMMARY_XPATH = '//ul[@class="book_profile"]/li[@class="book_bk_qs1"]/text()'
+
+    # Catalog XPaths
+    _VOLUME_TITLE_XPATH = '//div[@class="mulu"]/text()'
+    _VOLUME_CONTENT_XPATH = '//div[@class="Content_Frame"]'
+    _CHAPTER_LIST_XPATH = './/ul[@class="mulu_list"]/a'
+
+    # Chapter XPaths
+    _CHAPTER_TEXT_XPATH = (
+        '//div[@class="yuedu Content_Frame"]//div[@style="text-indent: 2em;"]/text()'
+    )
+    _CHAPTER_CONTENT_NODES_XPATH = (
+        '//div[@class="yuedu Content_Frame"]//div[@style="text-indent: 2em;"]/*'
+    )
+    _CHAPTER_TITLE_XPATH = '//ul[@class="menu_top_list book_view_top"]/li[2]/text()'
+
+    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.
+        """
+        if len(html_str) < 2:
+            return {}
+
+        info_tree = etree.HTML(html_str[0])
+        catalog_tree = etree.HTML(html_str[1])
+
+        result: dict[str, Any] = {}
+
+        # Book metadata
+        book_name = info_tree.xpath(self._BOOK_NAME_XPATH)
+        result["book_name"] = book_name[0].strip() if book_name else ""
+
+        book_info3 = info_tree.xpath(self._AUTHOR_INFO_XPATH)
+        result["author"] = book_info3[0].split("/")[0].strip() if book_info3 else ""
+        result["word_count"] = (
+            book_info3[0].split("/")[1].strip()
+            if book_info3 and len(book_info3[0].split("/")) > 1
+            else ""
+        )
+
+        book_info3_br = info_tree.xpath(self._UPDATE_TIME_XPATH)
+        result["update_time"] = book_info3_br[0].strip() if book_info3_br else ""
+
+        cover_url = info_tree.xpath(self._COVER_URL_XPATH)
+        result["cover_url"] = "https:" + cover_url[0] if cover_url else ""
+
+        serial_status = info_tree.xpath(self._STATUS_XPATH)
+        result["serial_status"] = next(
+            (s for s in serial_status if "完结" in s or "连载" in s), ""
+        )
+
+        summary = info_tree.xpath(self._SUMMARY_XPATH)
+        result["summary"] = "".join(summary).strip()
+
+        # Chapter structure
+        volume_titles = catalog_tree.xpath(self._VOLUME_TITLE_XPATH)
+        volume_blocks = catalog_tree.xpath(self._VOLUME_CONTENT_XPATH)
+
+        volumes = []
+        for vol_title, vol_block in zip(volume_titles, volume_blocks, strict=False):
+            chapters = []
+            for a in vol_block.xpath(self._CHAPTER_LIST_XPATH):
+                href = a.xpath("./@href")[0] if a.xpath("./@href") else ""
+                title = "".join(a.xpath(".//li//text()")).strip()
+                chapter_id = href.split("/")[-2] if href else ""
+                chapters.append(
+                    {
+                        "title": title,
+                        "url": href,
+                        "chapterId": chapter_id,
+                    }
+                )
+            volumes.append(
+                {
+                    "volume_name": vol_title.strip(),
+                    "chapters": 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:
+            return None
+        keywords = [
+            "本章为VIP章节",  # 本章为VIP章节，订阅后可立即阅读
+        ]
+        if any(kw in html_str[0] for kw in keywords):
+            return None
+        tree = etree.HTML(html_str[0])
+
+        content_lines: list[str] = []
+        content_nodes = tree.xpath(self._CHAPTER_CONTENT_NODES_XPATH)
+        for node in content_nodes:
+            tag = node.tag.lower()
+            if tag == "p":
+                text = "".join(node.xpath(".//text()")).strip()
+                if text:
+                    content_lines.append(text)
+            elif tag == "img":
+                src = node.get("src", "").strip()
+                if src:
+                    # embed image as HTML tag
+                    content_lines.append(f'<img src="{src}" />')
+
+        if not content_lines:
+            raw_text_parts = tree.xpath(self._CHAPTER_TEXT_XPATH)
+            content_lines = [txt.strip() for txt in raw_text_parts if txt.strip()]
+
+        content = "\n\n".join(content_lines).strip()
+        if not content:
+            return None
+
+        title_part = tree.xpath(self._CHAPTER_TITLE_XPATH)
+        title = title_part[0].strip() if title_part else ""
+
+        return {
+            "id": chapter_id,
+            "title": title,
+            "content": content,
+            "extra": {"site": "sfacg"},
+        }

novel_downloader/core/parsers/yamibo/__init__.py

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

novel_downloader/core/parsers/yamibo/main_parser.py

@@ -0,0 +1,194 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.parsers.yamibo.main_parser
+------------------------------------------------
+
+"""
+
+from typing import Any
+
+from lxml import etree
+
+from novel_downloader.core.parsers.base import BaseParser
+from novel_downloader.utils.chapter_storage import ChapterDict
+
+
+class YamiboParser(BaseParser):
+    """ """
+
+    BASE_URL = "https://www.yamibo.com"
+    # Book info XPaths
+    _BOOK_NAME_XPATH = 'string(//h3[contains(@class, "col-md-12")])'
+    _AUTHOR_XPATH = 'string(//h5[contains(@class, "text-warning")])'
+    _COVER_URL_XPATH = '//img[contains(@class, "img-responsive")]/@src'
+    _UPDATE_TIME_XPATH = '//p[contains(text(), "更新时间：")]'
+    _SERIAL_STATUS_XPATH = '//p[contains(text(), "作品状态：")]'
+    _TYPE_XPATH = '//p[contains(text(), "作品分类：")]'
+    _SUMMARY_XPATH = 'string(//div[@id="w0-collapse1"]/div)'
+
+    _VOLUME_NODE_XPATH = (
+        '//div[contains(@class, "panel-info") and contains(@class, "panel-default")]'
+    )
+    _VOLUME_TITLE_XPATH = './/div[contains(@class, "panel-heading")]//a/text()'
+    _CHAPTER_NODE_XPATH = (
+        './/div[contains(@class, "panel-body")]//a[contains(@href, "view-chapter")]'
+    )
+    _CHAPTER_FLAT_XPATH = (
+        '//div[@class="panel-body"]//a[contains(@href, "view-chapter")]'
+    )
+
+    # Chapter field XPaths
+    _CHAPTER_TITLE_XPATH = "string(//section[contains(@class, 'col-md-9')]//h3)"
+    _CHAPTER_TIME_XPATH = (
+        "//div[contains(@class, 'row')]//div[contains(text(), '更新时间')]"
+    )
+    _CHAPTER_WORD_COUNT_XPATH = (
+        "//div[contains(@class, 'row')]//div[contains(text(), '章节字数')]"
+    )
+    _CHAPTER_CONTENT_XPATH = "//div[@id='w0-collapse1']//p//text()"
+
+    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.
+        """
+        if not html_str:
+            return {}
+
+        tree = etree.HTML(html_str[0])
+        result: dict[str, Any] = {}
+
+        result["book_name"] = tree.xpath(self._BOOK_NAME_XPATH).strip()
+        result["author"] = tree.xpath(self._AUTHOR_XPATH).strip()
+
+        cover = tree.xpath(self._COVER_URL_XPATH)
+        result["cover_url"] = f"{self.BASE_URL}{cover[0]}" if cover else ""
+
+        update_node = tree.xpath(self._UPDATE_TIME_XPATH)
+        result["update_time"] = (
+            update_node[0].xpath("string()").replace("更新时间：", "").strip()
+            if update_node
+            else ""
+        )
+
+        serial_node = tree.xpath(self._SERIAL_STATUS_XPATH)
+        result["serial_status"] = (
+            serial_node[0].xpath("string()").replace("作品状态：", "").strip()
+            if serial_node
+            else ""
+        )
+
+        type_node = tree.xpath(self._TYPE_XPATH)
+        result["type"] = (
+            type_node[0].xpath("string()").replace("作品分类：", "").strip()
+            if type_node
+            else ""
+        )
+
+        result["summary"] = tree.xpath(self._SUMMARY_XPATH).strip()
+
+        volumes = []
+        volume_nodes = tree.xpath(self._VOLUME_NODE_XPATH)
+
+        if volume_nodes:
+            for volume_node in volume_nodes:
+                title_node = volume_node.xpath(self._VOLUME_TITLE_XPATH)
+                volume_name = title_node[0].strip() if title_node else "未命名卷"
+
+                chapter_nodes = volume_node.xpath(self._CHAPTER_NODE_XPATH)
+                chapters = []
+                for chap in chapter_nodes:
+                    title = chap.xpath("string()").strip()
+                    url = chap.get("href", "")
+                    chapter_id = url.split("id=")[-1] if "id=" in url else ""
+                    chapters.append(
+                        {
+                            "title": title,
+                            "url": url,
+                            "chapterId": chapter_id,
+                        }
+                    )
+
+                volumes.append(
+                    {
+                        "volume_name": volume_name,
+                        "chapters": chapters,
+                    }
+                )
+
+        else:
+            # fallback: flat list
+            chapter_nodes = tree.xpath(self._CHAPTER_FLAT_XPATH)
+            chapters = []
+            for chap in chapter_nodes:
+                title = chap.xpath("string()").strip()
+                url = chap.get("href", "")
+                chapter_id = url.split("id=")[-1] if "id=" in url else ""
+                chapters.append(
+                    {
+                        "title": title,
+                        "url": url,
+                        "chapterId": chapter_id,
+                    }
+                )
+
+            volumes = [
+                {
+                    "volume_name": "单卷",
+                    "chapters": 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:
+            return None
+        tree = etree.HTML(html_str[0])
+
+        content_lines = tree.xpath(self._CHAPTER_CONTENT_XPATH)
+        content = "\n\n".join(line.strip() for line in content_lines if line.strip())
+        if not content:
+            return None
+
+        title = tree.xpath(self._CHAPTER_TITLE_XPATH).strip()
+
+        update_node = tree.xpath(self._CHAPTER_TIME_XPATH)
+        updated_at = (
+            update_node[0].text.strip().replace("更新时间：", "") if update_node else ""
+        )
+
+        word_node = tree.xpath(self._CHAPTER_WORD_COUNT_XPATH)
+        word = word_node[0].text.strip().replace("章节字数：", "") if word_node else ""
+        word_count = int(word) if word.isdigit() else 0
+
+        return {
+            "id": chapter_id,
+            "title": title,
+            "content": content,
+            "extra": {
+                "site": "yamibo",
+                "word_count": word_count,
+                "updated_at": updated_at,
+            },
+        }

novel_downloader/core/requesters/__init__.py

@@ -9,27 +9,57 @@ to perform network interactions, such as logging in, sending requests,
 or interacting with browser/session-based sources.
 
 Subpackages:
-- common
-- biquge
-- qidian
+- 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 (
+    BiqugeAsyncSession,
     BiqugeSession,
 )
 from .common import (
     CommonAsyncSession,
     CommonSession,
 )
+from .esjzone import (
+    EsjzoneAsyncSession,
+    EsjzoneSession,
+)
+from .qianbi import (
+    QianbiAsyncSession,
+    QianbiSession,
+)
 from .qidian import (
     QidianBrowser,
     QidianSession,
 )
+from .sfacg import (
+    SfacgAsyncSession,
+    SfacgSession,
+)
+from .yamibo import (
+    YamiboAsyncSession,
+    YamiboSession,
+)
 
 __all__ = [
+    "BiqugeAsyncSession",
     "BiqugeSession",
     "CommonAsyncSession",
     "CommonSession",
+    "EsjzoneAsyncSession",
+    "EsjzoneSession",
+    "QianbiAsyncSession",
+    "QianbiSession",
     "QidianBrowser",
     "QidianSession",
+    "SfacgAsyncSession",
+    "SfacgSession",
+    "YamiboAsyncSession",
+    "YamiboSession",
 ]