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

novel_downloader/core/searchers/aaatxt.py

@@ -0,0 +1,107 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.searchers.aaatxt
+--------------------------------------
+
+"""
+
+import logging
+
+from lxml import html
+
+from novel_downloader.core.searchers.base import BaseSearcher
+from novel_downloader.core.searchers.registry import register_searcher
+from novel_downloader.models import SearchResult
+
+logger = logging.getLogger(__name__)
+
+
+@register_searcher(
+    site_keys=["aaatxt"],
+)
+class AaatxtSearcher(BaseSearcher):
+    site_name = "aaatxt"
+    priority = 500
+    SEARCH_URL = "http://www.aaatxt.com/search.php"
+
+    @classmethod
+    async def _fetch_html(cls, keyword: str) -> str:
+        # gbk / gb2312
+        params = {
+            "keyword": cls._quote(keyword, encoding="gb2312", errors="replace"),
+            "submit": cls._quote("搜 索", encoding="gb2312", errors="replace"),
+        }
+        full_url = cls._build_url(cls.SEARCH_URL, params)  # need build manually
+        headers = {
+            "Host": "www.aaatxt.com",
+            "Referer": "http://www.aaatxt.com/",
+        }
+        try:
+            async with (await cls._http_get(full_url, headers=headers)) as resp:
+                return await cls._response_to_str(resp, "gb2312")
+        except Exception:
+            logger.error(
+                "Failed to fetch HTML for keyword '%s' from '%s'",
+                keyword,
+                cls.SEARCH_URL,
+            )
+            return ""
+
+    @classmethod
+    def _parse_html(cls, html_str: str, limit: int | None = None) -> list[SearchResult]:
+        doc = html.fromstring(html_str)
+        rows = doc.xpath("//div[@class='sort']//div[@class='list']/table")
+        results: list[SearchResult] = []
+
+        for idx, row in enumerate(rows):
+            href = cls._first_str(row.xpath(".//td[@class='name']/h3/a/@href"))
+            if not href:
+                continue
+
+            if limit is not None and idx >= limit:
+                break
+
+            book_id = href.split("/")[-1].split(".")[0]
+            book_url = cls._abs_url(href)
+
+            cover_rel = cls._first_str(row.xpath(".//td[@class='cover']/a/img/@src"))
+            cover_url = cls._abs_url(cover_rel) if cover_rel else ""
+
+            title = cls._first_str(row.xpath(".//td[@class='name']/h3/a//text()"))
+
+            size_text = row.xpath("string(.//td[@class='size'])")
+            size_norm = size_text.replace("\u00a0", " ").replace(" ", " ").strip()
+            tokens = [t for t in size_norm.split() if t]
+
+            word_count = "-"
+            author = "-"
+            for tok in tokens:
+                if tok.startswith("大小:"):
+                    word_count = tok.split(":", 1)[1].strip()
+                elif tok.startswith("上传:"):
+                    author = tok.split(":", 1)[1].strip()
+
+            intro_text = row.xpath("string(.//td[@class='intro'])")
+            intro_norm = intro_text.replace("\u00a0", " ").replace(" ", " ")
+            update_date = "-"
+            for marker in ("更新:", "更新："):
+                if marker in intro_norm:
+                    tail = intro_norm.split(marker, 1)[1].strip()
+                    update_date = tail.split()[0] if tail else "-"
+                    break
+
+            results.append(
+                SearchResult(
+                    site=cls.site_name,
+                    book_id=book_id,
+                    book_url=book_url,
+                    cover_url=cover_url,
+                    title=title,
+                    author=author,
+                    latest_chapter="-",
+                    update_date=update_date,
+                    word_count=word_count,
+                    priority=cls.priority + idx,
+                )
+            )
+        return results

novel_downloader/core/searchers/{biquge.py → b520.py}

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 """
-novel_downloader.core.searchers.biquge
---------------------------------------
+novel_downloader.core.searchers.b520
+------------------------------------
 
 """
 
@@ -17,57 +17,53 @@ logger = logging.getLogger(__name__)
 
 
 @register_searcher(
-    site_keys=["biquge", "bqg"],
+    site_keys=["biquge", "bqg", "b520"],
 )
 class BiqugeSearcher(BaseSearcher):
     site_name = "biquge"
-    priority = 5
+    priority = 30
+    BASE_URL = "http://www.b520.cc/"
     SEARCH_URL = "http://www.b520.cc/modules/article/search.php"
 
     @classmethod
-    def _fetch_html(cls, keyword: str) -> str:
-        """
-        Fetch raw HTML from Biquge's search page.
-
-        :param keyword: The search term to query on Biquge.
-        :return: HTML text of the search results page, or an empty string on fail.
-        """
+    async def _fetch_html(cls, keyword: str) -> str:
         params = {"searchkey": keyword}
         try:
-            response = cls._http_get(cls.SEARCH_URL, params=params)
-            return response.text
+            async with (await cls._http_get(cls.SEARCH_URL, params=params)) as resp:
+                return await cls._response_to_str(resp)
         except Exception:
             logger.error(
                 "Failed to fetch HTML for keyword '%s' from '%s'",
                 keyword,
                 cls.SEARCH_URL,
-                exc_info=True,
             )
             return ""
 
     @classmethod
     def _parse_html(cls, html_str: str, limit: int | None = None) -> list[SearchResult]:
-        """
-        Parse raw HTML from Biquge search results into list of SearchResult.
-
-        :param html_str: Raw HTML string from Biquge search results page.
-        :param limit: Maximum number of results to return, or None for all.
-        :return: List of SearchResult dicts.
-        """
         doc = html.fromstring(html_str)
         rows = doc.xpath('//table[@class="grid"]//tr[position()>1]')
         results: list[SearchResult] = []
 
         for idx, row in enumerate(rows):
+            href = cls._first_str(row.xpath(".//td[1]/a[1]/@href"))
+            if not href:
+                continue
+
             if limit is not None and idx >= limit:
                 break
-            # Title and book_id
-            title_elem = row.xpath(".//td[1]/a")[0]
-            title = title_elem.text_content().strip()
-            href = title_elem.get("href", "").strip("/")
-            book_id = href.split("/")[0] if href else ""
-            # Author
-            author = row.xpath(".//td[3]")[0].text_content().strip()
+
+            book_id = href.strip("/").split("/")[-1]
+            book_url = cls._abs_url(href)
+
+            title = cls._first_str(row.xpath(".//td[1]/a[1]/text()"))
+
+            latest_chapter = cls._first_str(row.xpath(".//td[2]/a[1]/text()")) or "-"
+
+            author = cls._first_str(row.xpath(".//td[3]//text()"))
+            word_count = cls._first_str(row.xpath(".//td[4]//text()"))
+            update_date = cls._first_str(row.xpath(".//td[5]//text()"))
+
             # Compute priority
             prio = cls.priority + idx
 
@@ -75,8 +71,13 @@ class BiqugeSearcher(BaseSearcher):
                 SearchResult(
                     site=cls.site_name,
                     book_id=book_id,
+                    book_url=book_url,
+                    cover_url="",
                     title=title,
                     author=author,
+                    latest_chapter=latest_chapter,
+                    update_date=update_date,
+                    word_count=word_count,
                     priority=prio,
                 )
             )

novel_downloader/core/searchers/base.py

@@ -3,13 +3,14 @@
 novel_downloader.core.searchers.base
 ------------------------------------
 
+Abstract base class providing common utilities for site-specific searchers.
 """
 
 import abc
-from typing import Any
-from urllib.parse import quote_plus
+from typing import Any, ClassVar
+from urllib.parse import quote_plus, urljoin
 
-import requests
+import aiohttp
 
 from novel_downloader.core.interfaces import SearcherProtocol
 from novel_downloader.models import SearchResult
@@ -18,75 +19,150 @@ from novel_downloader.utils.constants import DEFAULT_USER_HEADERS
 
 class BaseSearcher(abc.ABC, SearcherProtocol):
     site_name: str
-    _session = requests.Session()
-    _DEFAULT_TIMEOUT: tuple[int, int] = (5, 10)
+    BASE_URL: str = ""
+    _session: ClassVar[aiohttp.ClientSession | None] = None
 
     @classmethod
-    def search(cls, keyword: str, limit: int | None = None) -> list[SearchResult]:
-        html = cls._fetch_html(keyword)
+    def configure(cls, session: aiohttp.ClientSession) -> None:
+        cls._session = session
+
+    @classmethod
+    async def search(cls, keyword: str, limit: int | None = None) -> list[SearchResult]:
+        html = await cls._fetch_html(keyword)
         return cls._parse_html(html, limit)
 
     @classmethod
     @abc.abstractmethod
-    def _fetch_html(cls, keyword: str) -> str:
-        """Get raw HTML from search API or page"""
+    async def _fetch_html(cls, keyword: str) -> str:
+        """
+        Fetch raw HTML from search API or page
+
+        :param keyword: The search term to query.
+        :return: HTML text of the search results page, or an empty string on fail.
+        """
         pass
 
     @classmethod
     @abc.abstractmethod
     def _parse_html(cls, html_str: str, limit: int | None = None) -> list[SearchResult]:
-        """Parse HTML into standard search result list"""
+        """
+        Parse raw HTML from search API or page into list of SearchResult.
+
+        :param html_str: Raw HTML string from search results page.
+        :param limit: Maximum number of results to return, or None for all.
+        :return: List of SearchResult dicts.
+        """
         pass
 
     @classmethod
-    def _http_get(
+    async def _http_get(
         cls,
         url: str,
         *,
         params: dict[str, str] | None = None,
         headers: dict[str, str] | None = None,
-        timeout: tuple[int, int] | None = None,
         **kwargs: Any,
-    ) -> requests.Response:
+    ) -> aiohttp.ClientResponse:
         """
-        Helper for GET requests with default headers, timeout, and error-raising.
+        Helper for GET requests with default headers.
         """
+        session = cls._ensure_session()
         hdrs = {**DEFAULT_USER_HEADERS, **(headers or {})}
-        resp = cls._session.get(
-            url,
-            params=params,
-            headers=hdrs,
-            timeout=timeout or cls._DEFAULT_TIMEOUT,
-            **kwargs,
-        )
-        resp.raise_for_status()
+        resp = await session.get(url, params=params, headers=hdrs, **kwargs)
+        try:
+            resp.raise_for_status()
+        except aiohttp.ClientResponseError:
+            try:
+                await resp.read()
+            finally:
+                resp.release()
+            raise
         return resp
 
     @classmethod
-    def _http_post(
+    async def _http_post(
         cls,
         url: str,
         *,
         data: dict[str, str] | str | None = None,
         headers: dict[str, str] | None = None,
-        timeout: tuple[int, int] | None = None,
         **kwargs: Any,
-    ) -> requests.Response:
+    ) -> aiohttp.ClientResponse:
         """
-        Helper for POST requests with default headers, timeout, and error-raising.
+        Helper for POST requests with default headers.
         """
+        session = cls._ensure_session()
         hdrs = {**DEFAULT_USER_HEADERS, **(headers or {})}
-        resp = cls._session.post(
-            url,
-            data=data,
-            headers=hdrs,
-            timeout=timeout or cls._DEFAULT_TIMEOUT,
-            **kwargs,
-        )
-        resp.raise_for_status()
+        resp = await session.post(url, data=data, headers=hdrs, **kwargs)
+        try:
+            resp.raise_for_status()
+        except aiohttp.ClientResponseError:
+            try:
+                await resp.read()
+            finally:
+                resp.release()
+            raise
         return resp
 
+    @classmethod
+    def _ensure_session(cls) -> aiohttp.ClientSession:
+        if cls._session is None:
+            raise RuntimeError(
+                f"{cls.__name__} has no aiohttp session. "
+                "Call .configure(session) first."
+            )
+        return cls._session
+
     @staticmethod
-    def _quote(q: str) -> str:
+    def _quote(q: str, encoding: str | None = None, errors: str | None = None) -> str:
         """URL-encode a query string safely."""
-        return quote_plus(q)
+        return quote_plus(q, encoding=encoding, errors=errors)
+
+    @staticmethod
+    async def _response_to_str(
+        resp: aiohttp.ClientResponse,
+        encoding: str | None = None,
+    ) -> str:
+        """
+        Read the full body of resp as text. First try the declared charset,
+        then on UnicodeDecodeError fall back to a lenient utf-8 decode.
+        """
+        data: bytes = await resp.read()
+        encodings = [
+            encoding,
+            resp.charset,
+            "gb2312",
+            "gb18030",
+            "gbk",
+            "utf-8",
+        ]
+        encodings_list: list[str] = [e for e in encodings if e]
+        for enc in encodings_list:
+            try:
+                return data.decode(enc)
+            except UnicodeDecodeError:
+                continue
+        encoding = encoding or "utf-8"
+        return data.decode(encoding, errors="ignore")
+
+    @staticmethod
+    def _first_str(xs: list[str], replaces: list[tuple[str, str]] | None = None) -> str:
+        replaces = replaces or []
+        value: str = xs[0].strip() if xs else ""
+        for replace in replaces:
+            old, new = replace
+            value = value.replace(old, new)
+        return value
+
+    @staticmethod
+    def _build_url(base: str, params: dict[str, str]) -> str:
+        query_string = "&".join(f"{k}={v}" for k, v in params.items())
+        return f"{base}?{query_string}"
+
+    @classmethod
+    def _abs_url(cls, url: str) -> str:
+        return (
+            url
+            if url.startswith(("http://", "https://"))
+            else urljoin(cls.BASE_URL, url)
+        )

novel_downloader/core/searchers/dxmwx.py

@@ -0,0 +1,105 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.searchers.dxmwx
+-------------------------------------
+
+"""
+
+import logging
+
+from lxml import html
+
+from novel_downloader.core.searchers.base import BaseSearcher
+from novel_downloader.core.searchers.registry import register_searcher
+from novel_downloader.models import SearchResult
+
+logger = logging.getLogger(__name__)
+
+
+@register_searcher(
+    site_keys=["dxmwx"],
+)
+class DxmwxSearcher(BaseSearcher):
+    site_name = "dxmwx"
+    priority = 30
+    BASE_URL = "https://www.dxmwx.org"
+    SEARCH_URL = "https://www.dxmwx.org/list/{query}.html"
+
+    @classmethod
+    async def _fetch_html(cls, keyword: str) -> str:
+        url = cls.SEARCH_URL.format(query=cls._quote(keyword))
+        try:
+            async with (await cls._http_get(url)) as resp:
+                return await cls._response_to_str(resp)
+        except Exception:
+            logger.error(
+                "Failed to fetch HTML for keyword '%s' from '%s'",
+                keyword,
+                cls.SEARCH_URL,
+            )
+            return ""
+
+    @classmethod
+    def _parse_html(cls, html_str: str, limit: int | None = None) -> list[SearchResult]:
+        doc = html.fromstring(html_str)
+        rows = doc.xpath(
+            "//div[@id='ListContents']/div[contains(@style,'position: relative')]"
+        )
+        results: list[SearchResult] = []
+
+        for idx, row in enumerate(rows):
+            href = cls._first_str(
+                row.xpath(".//div[contains(@class,'margin0h5')]//a[1]/@href")
+            )
+            if not href:
+                continue
+
+            if limit is not None and idx >= limit:
+                break
+
+            book_url = cls._abs_url(href)
+            # "/book/10409.html" -> "10409"
+            book_id = href.split("/")[-1].split(".", 1)[0]
+
+            title = cls._first_str(
+                row.xpath(".//div[contains(@class,'margin0h5')]//a[1]/text()")
+            )
+
+            author = cls._first_str(
+                row.xpath(".//div[contains(@class,'margin0h5')]//a[2]/text()")
+            )
+
+            cover_src = cls._first_str(
+                row.xpath(".//div[contains(@class,'imgwidth')]//img/@src")
+            )
+            cover_url = cls._abs_url(cover_src) if cover_src else ""
+
+            latest_chapter = cls._first_str(
+                row.xpath(
+                    ".//a[span and span[contains(normalize-space(.),'最新章节')]]"
+                    "/span/following-sibling::text()[1]"
+                )
+            )
+
+            update_date = cls._first_str(
+                row.xpath(".//span[contains(@class,'lefth5')]/text()")
+            )
+
+            # Compute priority
+            prio = cls.priority + idx
+
+            results.append(
+                SearchResult(
+                    site=cls.site_name,
+                    book_id=book_id,
+                    book_url=book_url,
+                    cover_url=cover_url,
+                    title=title,
+                    author=author,
+                    latest_chapter=latest_chapter,
+                    update_date=update_date,
+                    word_count="-",
+                    priority=prio,
+                )
+            )
+        return results

novel_downloader/core/searchers/eightnovel.py

@@ -0,0 +1,84 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.searchers.eightnovel
+------------------------------------------
+
+"""
+
+import logging
+
+from lxml import html
+
+from novel_downloader.core.searchers.base import BaseSearcher
+from novel_downloader.core.searchers.registry import register_searcher
+from novel_downloader.models import SearchResult
+
+logger = logging.getLogger(__name__)
+
+
+@register_searcher(
+    site_keys=["eightnovel", "8novel"],
+)
+class EightnovelSearcher(BaseSearcher):
+    site_name = "8novel"
+    priority = 20
+    BASE_URL = "https://www.8novel.com"
+    SEARCH_URL = "https://www.8novel.com/search/"
+
+    @classmethod
+    async def _fetch_html(cls, keyword: str) -> str:
+        params = {"key": keyword}
+        try:
+            async with (await cls._http_get(cls.SEARCH_URL, params=params)) as resp:
+                return await cls._response_to_str(resp)
+        except Exception:
+            logger.error(
+                "Failed to fetch HTML for keyword '%s' from '%s'",
+                keyword,
+                cls.SEARCH_URL,
+            )
+            return ""
+
+    @classmethod
+    def _parse_html(cls, html_str: str, limit: int | None = None) -> list[SearchResult]:
+        doc = html.fromstring(html_str)
+        anchors = doc.xpath("//div[contains(@class,'picsize')]/a")
+        results: list[SearchResult] = []
+
+        for idx, a in enumerate(anchors):
+            href = cls._first_str(a.xpath("./@href"))
+            if not href:
+                continue
+
+            if limit is not None and idx >= limit:
+                break
+
+            # '/novelbooks/6045' -> "6045"
+            book_id = href.rstrip("/").split("/")[-1]
+            book_url = cls._abs_url(href)
+
+            cover_rel = cls._first_str(a.xpath(".//img/@src"))
+            cover_url = cls._abs_url(cover_rel) if cover_rel else ""
+
+            title = cls._first_str(a.xpath("./@title"))
+
+            word_count = cls._first_str(a.xpath(".//eps//text()")) or "-"
+
+            # Compute priority
+            prio = cls.priority + idx
+
+            results.append(
+                SearchResult(
+                    site=cls.site_name,
+                    book_id=book_id,
+                    book_url=book_url,
+                    cover_url=cover_url,
+                    title=title,
+                    author="-",
+                    latest_chapter="-",
+                    update_date="-",
+                    word_count=word_count,
+                    priority=prio,
+                )
+            )
+        return results