novel-downloader 1.5.0__py3-none-any.whl → 2.0.0__py3-none-any.whl

novel_downloader/core/parsers/qbtr.py

@@ -0,0 +1,136 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.parsers.qbtr
+----------------------------------
+
+"""
+
+import re
+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=["qbtr"],
+)
+class QbtrParser(BaseParser):
+    """
+    Parser for 全本同人小说 book pages.
+    """
+
+    BASE_URL = "https://www.qbtr.cc"
+
+    def parse_book_info(
+        self,
+        html_list: list[str],
+        **kwargs: Any,
+    ) -> BookInfoDict | None:
+        if not html_list:
+            return None
+
+        # Parse the main info page
+        tree = html.fromstring(html_list[0])
+        # Book name
+        book_name = self._first_str(tree.xpath('//div[@class="infos"]/h1/text()'))
+        # Tags: the second breadcrumb (e.g., "同人小说")
+        tag = self._first_str(
+            tree.xpath('//div[contains(@class,"menNav")]/a[2]/text()')
+        )
+        tags = [tag] if tag else []
+
+        # Author & update_time from the date div
+        date_div = tree.xpath('//div[@class="date"]')
+        date_text = html.tostring(date_div[0], encoding="unicode", method="text")
+        author_match = re.search(r"作者[：:]\s*([^日]+)", date_text)
+        author = author_match.group(1).strip() if author_match else ""
+        date_match = re.search(r"日期[：:]\s*([\d-]+)", date_text)
+        update_time = date_match.group(1) if date_match else ""
+
+        # Summary from the <p> inside infos
+        paras = tree.xpath('//div[@class="infos"]/p//text()')
+        summary = "\n".join(p.strip() for p in paras if p.strip())
+
+        # Chapters from the book_list
+        chapters: list[ChapterInfoDict] = []
+        for a in tree.xpath('//div[contains(@class,"book_list")]//li/a'):
+            url = a.get("href", "").strip()
+            title = a.text_content().strip()
+            # General regex: /{category}/{bookId}/{chapterId}.html
+            m = re.search(r"^/[^/]+/\d+/(\d+)\.html$", url)
+            cid = m.group(1) if m else ""
+            chapters.append({"title": title, "url": url, "chapterId": cid})
+
+        volumes: list[VolumeInfoDict] = [{"volume_name": "正文", "chapters": chapters}]
+
+        # Parse the download page (second HTML)
+        download_url = ""
+        if len(html_list) > 1 and html_list[1]:
+            dtree = html.fromstring(html_list[1])
+            a = dtree.xpath('//a[@id="dowloadnUrl"]')
+            if a:
+                link = a[0].get("link") or a[0].get("href") or ""
+                download_url = self._fix_download_link(link)
+
+        return {
+            "book_name": book_name,
+            "author": author,
+            "cover_url": "",
+            "update_time": update_time,
+            "tags": tags,
+            "summary": summary,
+            "volumes": volumes,
+            "extra": {"download_url": download_url},
+        }
+
+    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])
+
+        raw_title = self._first_str(
+            tree.xpath('//div[contains(@class,"read_chapterName")]//h1/text()')
+        )
+
+        crumbs = tree.xpath('//div[contains(@class,"readTop")]//a/text()')
+        book_name = crumbs[-1].strip() if crumbs else ""
+
+        title = raw_title.replace(book_name, "").strip()
+
+        paragraphs = tree.xpath('//div[contains(@class,"read_chapterDetail")]/p')
+        texts = []
+        for p in paragraphs:
+            txt = p.text_content().strip()
+            if txt:
+                texts.append(txt)
+
+        content = "\n".join(texts)
+        if not content:
+            return None
+
+        return {
+            "id": chapter_id,
+            "title": title,
+            "content": content,
+            "extra": {"site": "qbtr"},
+        }
+
+    @classmethod
+    def _fix_download_link(cls, link: str) -> str:
+        true_link = link.replace("qb../", "/e/DownSys/")
+        return f"{cls.BASE_URL}{true_link}"

novel_downloader/core/parsers/qianbi.py

@@ -12,63 +12,60 @@ 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=["qianbi"],
-    backends=["session", "browser"],
 )
 class QianbiParser(BaseParser):
-    """ """
+    """
+    Parser for 铅笔小说 book pages.
+    """
 
     def parse_book_info(
         self,
         html_list: list[str],
         **kwargs: Any,
-    ) -> dict[str, Any]:
-        """
-        Parse a book info page and extract metadata and chapter structure.
-
-        :param html_list: Raw HTML of the book info pages.
-        :return: Parsed metadata and chapter structure as a dictionary.
-        """
+    ) -> BookInfoDict | None:
         if len(html_list) < 2:
-            return {}
+            return None
 
         info_tree = html.fromstring(html_list[0])
         catalog_tree = html.fromstring(html_list[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()'
+        book_name = self._first_str(info_tree.xpath('//h1[@class="page-title"]/text()'))
+        author = self._first_str(
+            info_tree.xpath('//a[contains(@href,"/author/")]/@title')
+        )
+        cover_url = self._first_str(
+            info_tree.xpath('//div[@class="novel-cover"]//img/@data-src')
+        )
+        serial_status = self._first_str(
+            info_tree.xpath(
+                '//a[@class="tag-link" and (text()="完结" or text()="连载")]/text()'
+            )
+        )
+        word_count = self._first_str(
+            info_tree.xpath('//span[contains(text(), "字")]/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"] = summary_node[0].text_content().strip()
+            summary = str(summary_node[0].text_content()).strip()
         else:
-            result["summary"] = ""
+            summary = ""
 
-        result["update_time"] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+        update_time = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
 
-        volumes: list[dict[str, Any]] = []
-        current_volume = None
+        volumes: list[VolumeInfoDict] = []
+        current_volume: VolumeInfoDict | None = None
 
         for elem in catalog_tree.xpath('//div[@class="box"]/*'):
             class_attr = elem.get("class", "")
@@ -104,9 +101,17 @@ class QianbiParser(BaseParser):
         if current_volume:
             volumes.append(current_volume)
 
-        result["volumes"] = volumes
-
-        return result
+        return {
+            "book_name": book_name,
+            "author": author,
+            "cover_url": cover_url,
+            "update_time": update_time,
+            "word_count": word_count,
+            "serial_status": serial_status,
+            "summary": summary,
+            "volumes": volumes,
+            "extra": {},
+        }
 
     def parse_chapter(
         self,
@@ -114,31 +119,24 @@ class QianbiParser(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:
             return None
         tree = html.fromstring(html_list[0])
 
+        # Content paragraphs
         paras = tree.xpath('//div[@class="article-content"]/p/text()')
-        content_text = "\n\n".join(p.strip() for p in paras if p.strip())
+        content_text = "\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 ""
+        title_text = self._first_str(tree.xpath('//h1[@class="article-title"]/text()'))
+        volume_text = self._first_str(tree.xpath('//h3[@class="text-muted"]/text()'))
 
-        volume = tree.xpath('//h3[@class="text-muted"]/text()')
-        volume_text = volume[0].strip() if volume else ""
-
-        next_href = tree.xpath('//div[@class="footer"]/a[@class="f-right"]/@href')
+        next_href = self._first_str(
+            tree.xpath('//div[@class="footer"]/a[@class="f-right"]/@href')
+        )
         next_chapter_id = (
-            next_href[0].split("/")[-1].replace(".html", "") if next_href else ""
+            next_href.split("/")[-1].replace(".html", "") if next_href else ""
         )
 
         return {

novel_downloader/core/parsers/qidian/book_info_parser.py

@@ -12,10 +12,11 @@ time, status, word count, summary, and volume-chapter structure.
 import logging
 import re
 from datetime import datetime
-from typing import Any
 
 from lxml import html
 
+from novel_downloader.models import BookInfoDict, ChapterInfoDict, VolumeInfoDict
+
 logger = logging.getLogger(__name__)
 
 
@@ -23,7 +24,7 @@ def _chapter_url_to_id(url: str) -> str:
     return url.rstrip("/").split("/")[-1]
 
 
-def parse_book_info(html_str: str) -> dict[str, Any]:
+def parse_book_info(html_str: str) -> BookInfoDict | None:
     """
     Extract metadata: title, author, cover_url, update_time, status,
     word_count, summary, and volumes with chapters.
@@ -31,60 +32,58 @@ def parse_book_info(html_str: str) -> dict[str, Any]:
     :param html_str: Raw HTML of the book info page.
     :return: A dict containing book metadata.
     """
-    info: dict[str, Any] = {}
-    try:
-        doc = html.fromstring(html_str)
-
-        info["book_name"] = doc.xpath('string(//h1[@id="bookName"])').strip()
-
-        info["author"] = doc.xpath('string(//a[@class="writer-name"])').strip()
-
-        book_id = doc.xpath('//a[@id="bookImg"]/@data-bid')[0]
-        info[
-            "cover_url"
-        ] = f"https://bookcover.yuewen.com/qdbimg/349573/{book_id}/600.webp"
-
-        ut = (
-            doc.xpath('string(//span[@class="update-time"])')
-            .replace("更新时间:", "")
-            .strip()
-        )
-        if re.match(r"^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}$", ut):
-            info["update_time"] = ut
-        else:
-            info["update_time"] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-
-        info["serial_status"] = doc.xpath(
-            'string(//p[@class="book-attribute"]/span[1])'
-        ).strip()
-
-        tags = doc.xpath('//p[contains(@class,"all-label")]//a/text()')
-        info["tags"] = [t.strip() for t in tags if t.strip()]
-
-        info["word_count"] = doc.xpath('string(//p[@class="count"]/em[1])').strip()
-
-        summary = doc.xpath('string(//p[@class="intro"])').strip()
-        info["summary_brief"] = summary
-
-        raw = doc.xpath('//p[@id="book-intro-detail"]//text()')
-        info["summary"] = "\n".join(line.strip() for line in raw if line.strip())
-
-        volumes = []
-        for vol in doc.xpath('//div[@id="allCatalog"]//div[@class="catalog-volume"]'):
-            vol_name = vol.xpath('string(.//h3[@class="volume-name"])').strip()
-            vol_name = vol_name.split(chr(183))[0].strip()
-            chapters = []
-            for li in vol.xpath('.//ul[contains(@class,"volume-chapters")]/li'):
-                a = li.xpath('.//a[@class="chapter-name"]')[0]
-                title = a.text.strip()
-                url = a.get("href")
-                chapters.append(
-                    {"title": title, "url": url, "chapterId": _chapter_url_to_id(url)}
-                )
-            volumes.append({"volume_name": vol_name, "chapters": chapters})
-        info["volumes"] = volumes
-
-    except Exception as e:
-        logger.warning("[Parser] Error parsing book info: %s", e)
-
-    return info
+    doc = html.fromstring(html_str)
+
+    book_name = doc.xpath('string(//h1[@id="bookName"])').strip()
+
+    author = doc.xpath('string(//a[@class="writer-name"])').strip()
+
+    book_id = doc.xpath('//a[@id="bookImg"]/@data-bid')[0]
+    cover_url = f"https://bookcover.yuewen.com/qdbimg/349573/{book_id}/600.webp"
+
+    ut = doc.xpath('string(//span[@class="update-time"])')
+    ut = ut.replace("更新时间:", "").strip()
+    if re.match(r"^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}$", ut):
+        update_time = ut
+    else:
+        update_time = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+
+    serial_status = doc.xpath('string(//p[@class="book-attribute"]/span[1])').strip()
+
+    tags_elem = doc.xpath('//p[contains(@class,"all-label")]//a/text()')
+    tags = [t.strip() for t in tags_elem if t.strip()]
+
+    word_count = doc.xpath('string(//p[@class="count"]/em[1])').strip()
+
+    summary_brief = doc.xpath('string(//p[@class="intro"])').strip()
+
+    raw = doc.xpath('//p[@id="book-intro-detail"]//text()')
+    summary = "\n".join(line.strip() for line in raw if line.strip())
+
+    volumes: list[VolumeInfoDict] = []
+    for vol in doc.xpath('//div[@id="allCatalog"]//div[@class="catalog-volume"]'):
+        vol_name = vol.xpath('string(.//h3[@class="volume-name"])').strip()
+        vol_name = vol_name.split(chr(183))[0].strip()
+        chapters: list[ChapterInfoDict] = []
+        for li in vol.xpath('.//ul[contains(@class,"volume-chapters")]/li'):
+            a = li.xpath('.//a[@class="chapter-name"]')[0]
+            title = a.text.strip()
+            url = a.get("href")
+            chapters.append(
+                {"title": title, "url": url, "chapterId": _chapter_url_to_id(url)}
+            )
+        volumes.append({"volume_name": vol_name, "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": tags,
+        "summary_brief": summary_brief,
+        "summary": summary,
+        "volumes": volumes,
+        "extra": {},
+    }