novel-downloader 1.5.0__py3-none-any.whl → 2.0.1__py3-none-any.whl

novel_downloader/core/parsers/esjzone.py

@@ -12,26 +12,20 @@ from lxml import html
 
 from novel_downloader.core.parsers.base import BaseParser
 from novel_downloader.core.parsers.registry import register_parser
-from novel_downloader.models import ChapterDict
+from novel_downloader.models import (
+    BookInfoDict,
+    ChapterDict,
+    VolumeInfoDict,
+)
 
 
 @register_parser(
     site_keys=["esjzone"],
-    backends=["session", "browser"],
 )
 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()'
+    """
+    Parser for esjzone book pages.
+    """
 
     # Chapter XPaths
     _CHAPTER_TEXT_XPATH = 'string(//div[contains(@class, "forum-content")])'
@@ -40,14 +34,13 @@ class EsjzoneParser(BaseParser):
         '//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_list: list[str],
         **kwargs: Any,
-    ) -> dict[str, Any]:
+    ) -> BookInfoDict | None:
         """
         Parse a book info page and extract metadata and chapter structure.
 
@@ -58,27 +51,40 @@ class EsjzoneParser(BaseParser):
         :return: Parsed metadata and chapter structure as a dictionary.
         """
         if not html_list or self._is_forum_page(html_list):
-            return {}
+            return None
+
         tree = html.fromstring(html_list[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
+
+        # --- Basic metadata ---
+        book_name = self._first_str(
+            tree.xpath('//h2[contains(@class,"text-normal")]/text()')
         )
-        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)
+        author = self._first_str(tree.xpath('//li[strong[text()="作者:"]]/a/text()'))
+        cover_url = self._first_str(
+            tree.xpath('//div[contains(@class,"product-gallery")]//img/@src')
+        )
+        update_time = self._first_str(
+            tree.xpath('//li[strong[text()="更新日期:"]]/text()')
+        )  # noqa: E501
+        word_count = self._first_str(
+            tree.xpath('//span[@id="txt"]/text()'), replaces=[(",", "")]
+        )
+        book_type = self._first_str(tree.xpath('//li[strong[text()="類型:"]]/text()'))
+        alt_name = self._first_str(
+            tree.xpath('//li[strong[text()="其他書名:"]]/text()')
+        )  # noqa: E501
+        web_url = self._first_str(tree.xpath('//li[strong[text()="Web生肉:"]]/a/@href'))
+
+        # Summary paragraphs
         paras = tree.xpath('//div[@class="description"]/p')
         texts = [p.xpath("string()").strip() for p in paras]
-        result["summary"] = "\n".join(texts).strip()
+        summary = "\n".join(t for t in texts if t)
 
-        volumes: list[dict[str, Any]] = []
-        current_vol: dict[str, Any] = {}
+        current_vol: VolumeInfoDict = {
+            "volume_name": "單卷",
+            "chapters": [],
+        }
+        volumes: list[VolumeInfoDict] = [current_vol]
 
         def _is_garbage_title(name: str) -> bool:
             stripped = name.strip()
@@ -89,25 +95,18 @@ class EsjzoneParser(BaseParser):
             if _is_garbage_title(name):
                 return
             name = name.strip() or "未命名卷"
-            if name == "未命名卷" and current_vol is not None:
+            if current_vol and current_vol["volume_name"] == name:
                 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)]'
-        # )
         nodes = tree.xpath('//div[@id="chapterList"]/*')
-
         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"
+                vol_name = node.xpath("string(./summary)").strip() or "未命名卷"
                 _start_volume(vol_name)
 
                 # all chapters inside this details
@@ -116,7 +115,11 @@ class EsjzoneParser(BaseParser):
                     href = a.get("href", "")
                     chap_id = href.rstrip("/").split("/")[-1].split(".", 1)[0]
                     current_vol["chapters"].append(
-                        {"title": title, "url": href, "chapterId": chap_id}
+                        {
+                            "title": title,
+                            "url": href,
+                            "chapterId": chap_id,
+                        }
                     )
 
             elif (
@@ -125,9 +128,9 @@ class EsjzoneParser(BaseParser):
                 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>
+                # * <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":
@@ -139,9 +142,21 @@ class EsjzoneParser(BaseParser):
                     {"title": title, "url": href, "chapterId": chap_id}
                 )
         volumes = [vol for vol in volumes if vol["chapters"]]
-        result["volumes"] = volumes
 
-        return result
+        return {
+            "book_name": book_name,
+            "author": author,
+            "cover_url": cover_url,
+            "update_time": update_time,
+            "summary": summary,
+            "tags": [book_type],
+            "word_count": word_count,
+            "volumes": volumes,
+            "extra": {
+                "alt_name": alt_name,
+                "web_url": web_url,
+            },
+        }
 
     def parse_chapter(
         self,
@@ -149,16 +164,9 @@ class EsjzoneParser(BaseParser):
         chapter_id: str,
         **kwargs: Any,
     ) -> ChapterDict | None:
-        """
-        Parse a single chapter page and extract clean text or simplified HTML.
-
-        :param html_list: 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_list or self._is_forum_page(html_list):
             return None
-        tree = html.fromstring(html_list[0], parser=None)
+        tree = html.fromstring(html_list[0])
 
         content_lines: list[str] = []
         content_nodes = tree.xpath(self._CHAPTER_CONTENT_NODES_XPATH)
@@ -178,7 +186,7 @@ class EsjzoneParser(BaseParser):
                     content_lines.append(f'<img src="{src}" />')
 
         content = (
-            "\n\n".join(content_lines).strip()
+            "\n".join(content_lines).strip()
             if content_lines
             else tree.xpath(self._CHAPTER_TEXT_XPATH).strip()
         )
@@ -216,16 +224,3 @@ class EsjzoneParser(BaseParser):
         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: html.HtmlElement,
-        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/guidaye.py

@@ -0,0 +1,128 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.parsers.guidaye
+-------------------------------------
+
+"""
+
+import re
+from datetime import datetime
+from typing import Any
+
+from lxml import html
+
+from novel_downloader.core.parsers.base import BaseParser
+from novel_downloader.core.parsers.registry import register_parser
+from novel_downloader.models import (
+    BookInfoDict,
+    ChapterDict,
+    VolumeInfoDict,
+)
+
+
+@register_parser(
+    site_keys=["guidaye"],
+)
+class GuidayeParser(BaseParser):
+    """
+    Parser for 名著阅读 book pages.
+    """
+
+    BASE_URL = "https://b.guidaye.com"
+
+    def parse_book_info(
+        self,
+        html_list: list[str],
+        **kwargs: Any,
+    ) -> BookInfoDict | None:
+        if not html_list:
+            return None
+
+        tree = html.fromstring(html_list[0])
+
+        # Book metadata
+        book_name = self._first_str(tree.xpath('//h1[@class="page-title"]/a/text()'))
+        author = self._first_str(
+            tree.xpath('//div[@id="category-description-author"]/a/text()')
+        )
+        cover_url = self.BASE_URL + self._first_str(
+            tree.xpath('//div[@id="category-description-image"]//img/@src')
+        )
+
+        # Summary paragraphs
+        summary = (
+            tree.xpath('string(//div[@id="category-description-text"])')
+            .replace("内容简介：", "", 1)
+            .strip()
+        )
+
+        # Chapter volumes & listings
+        volumes: list[VolumeInfoDict] = []
+        curr_vol: VolumeInfoDict = {"volume_name": "未命名卷", "chapters": []}
+
+        items = tree.xpath('//div[@class="entry-content"]/ul/*')
+        for elem in items:
+            if elem.tag.lower() == "h3":
+                # Flush previous volume
+                if curr_vol["chapters"]:
+                    volumes.append(curr_vol)
+                curr_vol = {"volume_name": elem.text_content().strip(), "chapters": []}
+            elif elem.tag.lower() == "li":
+                link = elem.xpath(".//a")[0]
+                href = link.get("href", "").strip()
+                title = link.get("title", "").strip()
+                cid_match = re.search(r"/(\d+)\.html$", href)
+                chapter_id = cid_match.group(1) if cid_match else ""
+                curr_vol["chapters"].append(
+                    {"title": title, "url": href, "chapterId": chapter_id}
+                )
+
+        # Append last volume
+        if curr_vol["chapters"]:
+            volumes.append(curr_vol)
+
+        # Timestamp of parsing
+        share_text = tree.xpath('string(//div[@id="category-description-share"])')
+        m = re.search(r"最近更新[：:]\s*([\d-]+)", share_text)
+        update_time = m.group(1) if m else datetime.now().strftime("%Y-%m-%d")
+
+        return {
+            "book_name": book_name,
+            "author": author,
+            "cover_url": cover_url,
+            "update_time": update_time,
+            "summary": summary,
+            "volumes": volumes,
+            "extra": {},
+        }
+
+    def parse_chapter(
+        self,
+        html_list: list[str],
+        chapter_id: str,
+        **kwargs: Any,
+    ) -> ChapterDict | None:
+        if not html_list:
+            return None
+        tree = html.fromstring(html_list[0])
+
+        # Title from entry-title
+        title = self._first_str(tree.xpath('//h1[@class="entry-title"]/text()'))
+
+        # Extract paragraphs within entry-content
+        full_text = tree.xpath('string(//div[@class="entry-content"])')
+        full_text = full_text.replace("\u00A0", " ")
+
+        # 3. Split into lines and clean up
+        lines = [line.strip() for line in full_text.splitlines() if line.strip()]
+        if not lines:
+            return None
+
+        content = "\n".join(lines)
+
+        return {
+            "id": chapter_id,
+            "title": title,
+            "content": content,
+            "extra": {"site": "guidaye"},
+        }

novel_downloader/core/parsers/hetushu.py

@@ -0,0 +1,139 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.parsers.hetushu
+-------------------------------------
+
+"""
+
+import re
+from datetime import datetime
+from typing import Any
+
+from lxml import html
+
+from novel_downloader.core.parsers.base import BaseParser
+from novel_downloader.core.parsers.registry import register_parser
+from novel_downloader.models import (
+    BookInfoDict,
+    ChapterDict,
+    VolumeInfoDict,
+)
+
+
+@register_parser(
+    site_keys=["hetushu"],
+)
+class HetushuParser(BaseParser):
+    """
+    Parser for 和图书 book pages.
+    """
+
+    BASE_URL = "https://www.hetushu.com"
+
+    def parse_book_info(
+        self,
+        html_list: list[str],
+        **kwargs: Any,
+    ) -> BookInfoDict | None:
+        if not html_list:
+            return None
+
+        tree = html.fromstring(html_list[0])
+
+        # --- Metadata ---
+        book_name = self._first_str(
+            tree.xpath('//div[contains(@class,"book_info")]/h2/text()')
+        )
+        author = self._first_str(
+            tree.xpath(
+                '//div[contains(@class,"book_info")]/div[contains(.,"作者")]/a/text()'
+            )
+        )
+        cover_url = self.BASE_URL + self._first_str(
+            tree.xpath('//div[contains(@class,"book_info")]//img/@src')
+        )
+
+        cls_attr = self._first_str(
+            tree.xpath('//div[contains(@class,"book_info")]/@class')
+        )
+        serial_status = "已完结" if "finish" in cls_attr else "连载中"
+
+        tags = [
+            a.strip()
+            for a in tree.xpath('//dl[@class="tag"]//dd/a/text()')
+            if a.strip()
+        ]
+
+        paras = tree.xpath('//div[@class="intro"]/p/text()')
+        summary = "\n".join(p.strip() for p in paras if p.strip())
+
+        # --- Chapter volumes & listings ---
+        volumes: list[VolumeInfoDict] = []
+        curr_vol: VolumeInfoDict = {"volume_name": "未命名卷", "chapters": []}
+
+        for elem in tree.xpath('//dl[@id="dir"]/*'):
+            if elem.tag == "dt":
+                # Start a new volume
+                if curr_vol["chapters"]:
+                    volumes.append(curr_vol)
+                curr_vol = {
+                    "volume_name": elem.text_content().strip(),
+                    "chapters": [],
+                }
+            elif elem.tag == "dd":
+                link = elem.xpath(".//a")[0]
+                href = link.get("href", "").strip()
+                title = link.get("title", "").strip()
+                # Extract numeric chapterId from the URL
+                m = re.search(r"/book/\d+/(?P<id>\d+)\.html", href)
+                chapter_id = m.group("id") if m else ""
+                curr_vol["chapters"].append(
+                    {"title": title, "url": href, "chapterId": chapter_id}
+                )
+
+        # Append the last volume if it has any chapters
+        if curr_vol["chapters"]:
+            volumes.append(curr_vol)
+
+        update_time = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+
+        return {
+            "book_name": book_name,
+            "author": author,
+            "cover_url": cover_url,
+            "update_time": update_time,
+            "serial_status": serial_status,
+            "tags": tags,
+            "summary": summary,
+            "volumes": volumes,
+            "extra": {},
+        }
+
+    def parse_chapter(
+        self,
+        html_list: list[str],
+        chapter_id: str,
+        **kwargs: Any,
+    ) -> ChapterDict | None:
+        if not html_list:
+            return None
+
+        tree = html.fromstring(html_list[0])
+
+        title = self._first_str(
+            tree.xpath('//div[@id="content"]//h2[@class="h2"]/text()')
+        )
+
+        paras = tree.xpath('//div[@id="content"]/div[not(@class)]/text()')
+        paragraph_texts = [p.strip() for p in paras if p.strip()]
+
+        content = "\n".join(paragraph_texts)
+        if not content.strip():
+            return None
+
+        return {
+            "id": chapter_id,
+            "title": title,
+            "content": content,
+            "extra": {"site": "hetushu"},
+        }

novel_downloader/core/parsers/i25zw.py

@@ -0,0 +1,137 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.parsers.i25zw
+-----------------------------------
+
+"""
+
+from typing import Any
+
+from lxml import html
+
+from novel_downloader.core.parsers.base import BaseParser
+from novel_downloader.core.parsers.registry import register_parser
+from novel_downloader.models import (
+    BookInfoDict,
+    ChapterDict,
+    ChapterInfoDict,
+    VolumeInfoDict,
+)
+
+
+@register_parser(
+    site_keys=["i25zw"],
+)
+class I25zwParser(BaseParser):
+    """
+    Parser for 25中文网 book-info pages.
+    """
+
+    def parse_book_info(
+        self,
+        html_list: list[str],
+        **kwargs: Any,
+    ) -> BookInfoDict | None:
+        if len(html_list) < 2:
+            return None
+
+        info_tree = html.fromstring(html_list[0])
+        catalog_tree = html.fromstring(html_list[1])
+
+        # Metadata extraction
+        book_name = self._first_str(info_tree.xpath("//h1[@class='f21h']/text()"))
+        author = self._first_str(info_tree.xpath("//h1[@class='f21h']/em/a/text()"))
+        cover_url = self._first_str(info_tree.xpath("//div[@class='pic']/img/@src"))
+
+        # Tags, status, word count, update time
+        tag = self._first_str(
+            info_tree.xpath("//b[contains(text(),'小说分类')]/parent::td/text()")
+        )
+        serial_status = self._first_str(
+            info_tree.xpath("//b[contains(text(),'小说状态')]/parent::td/text()")
+        )
+        word_count = self._first_str(
+            info_tree.xpath("//b[contains(text(),'全文字数')]/parent::td/text()")
+        )
+        raw_update = self._first_str(
+            info_tree.xpath("//b[contains(text(),'更新时间')]/parent::td/text()")
+        )
+        update_time = raw_update.strip("()")
+
+        # Summary from styled intro div
+        full_intro = info_tree.xpath("string(//div[@class='intro'][@style])").strip()
+        summary = full_intro.replace(f"关于{book_name}：", "", 1).strip()
+
+        # Chapter list extraction
+        dl = catalog_tree.xpath("//div[@id='list']/dl")[0]
+        # Full-text section dd's
+        dds = dl.xpath("./dd[preceding-sibling::dt[1][contains(., '正文')]]/a")
+        if not dds:
+            # Fallback to second <dt>'s following <dd>
+            dds = dl.xpath("./dt[2]/following-sibling::dd/a")
+
+        chapters: list[ChapterInfoDict] = []
+        for a in dds:
+            url = a.get("href", "").strip()
+            title = a.text_content().strip()
+            # '/311006/252845677.html' -> '252845677'
+            chapter_id = url.split("/")[-1].split(".")[0]
+            chapters.append(
+                {
+                    "title": title,
+                    "url": url,
+                    "chapterId": chapter_id,
+                }
+            )
+        volumes: list[VolumeInfoDict] = [{"volume_name": "正文", "chapters": chapters}]
+
+        return {
+            "book_name": book_name,
+            "author": author,
+            "cover_url": cover_url,
+            "update_time": update_time,
+            "word_count": word_count,
+            "serial_status": serial_status,
+            "tags": [tag] if tag else [],
+            "summary": summary,
+            "volumes": volumes,
+            "extra": {},
+        }
+
+    def parse_chapter(
+        self,
+        html_list: list[str],
+        chapter_id: str,
+        **kwargs: Any,
+    ) -> ChapterDict | None:
+        if not html_list:
+            return None
+
+        tree = html.fromstring(html_list[0])
+
+        title_text = self._first_str(
+            tree.xpath("//div[@class='zhangjieming']/h1/text()")
+        )
+
+        content_divs = tree.xpath("//div[@id='content']")
+        if not content_divs:
+            return None
+        content_div = content_divs[0]
+
+        # Only select direct <p> children to avoid nav links
+        paragraphs = []
+        for p in content_div.xpath("./p"):
+            text = p.text_content().strip()
+            if text:
+                paragraphs.append(text)
+
+        content_text = "\n".join(paragraphs)
+        if not content_text.strip():
+            return None
+
+        return {
+            "id": chapter_id,
+            "title": title_text,
+            "content": content_text,
+            "extra": {"site": "i25zw"},
+        }