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

novel_downloader/core/searchers/qbtr.py

@@ -0,0 +1,106 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.searchers.qbtr
+------------------------------------
+
+"""
+
+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=["qbtr"],
+)
+class QbtrSearcher(BaseSearcher):
+    site_name = "qbtr"
+    priority = 30
+    BASE_URL = "https://www.qbtr.cc"
+    SEARCH_URL = "https://www.qbtr.cc/e/search/index.php"
+
+    @classmethod
+    async def _fetch_html(cls, keyword: str) -> str:
+        keyboard = cls._quote(keyword, encoding="gbk", errors="replace")
+        show = "title"
+        classid = "0"
+        body = f"keyboard={keyboard}&show={show}&classid={classid}"
+        headers = {
+            "Origin": "https://www.qbtr.cc",
+            "Referer": "https://www.qbtr.cc/",
+            "Content-Type": "application/x-www-form-urlencoded",
+        }
+        try:
+            async with (
+                await cls._http_post(cls.SEARCH_URL, data=body, headers=headers)
+            ) 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[@class="books m-cols"]/div[@class="bk"]')
+        results: list[SearchResult] = []
+
+        for idx, row in enumerate(rows):
+            href = cls._first_str(row.xpath(".//h3/a[1]/@href"))
+            if not href:
+                continue
+
+            if limit is not None and idx >= limit:
+                break
+
+            # '/tongren/8850.html' -> "tongren-8850"
+            book_id = href.strip("/").split(".")[0].replace("/", "-")
+            book_url = cls._abs_url(href)
+
+            title = cls._first_str(row.xpath(".//h3/a[1]//text()"))
+
+            author = (
+                cls._first_str(
+                    row.xpath(".//div[contains(@class,'booknews')]/text()"),
+                    replaces=[("作者：", "")],
+                )
+                or "-"
+            )
+
+            update_date = (
+                cls._first_str(
+                    row.xpath(
+                        ".//div[contains(@class,'booknews')]/label[contains(@class,'date')]/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="",
+                    title=title,
+                    author=author,
+                    latest_chapter="-",
+                    update_date=update_date,
+                    word_count="-",
+                    priority=prio,
+                )
+            )
+        return results

novel_downloader/core/searchers/qianbi.py

@@ -1,12 +1,11 @@
 #!/usr/bin/env python3
 """
 novel_downloader.core.searchers.qianbi
------------------------------------------
+--------------------------------------
 
 """
 
 import logging
-import re
 
 from lxml import html
 
@@ -22,39 +21,26 @@ logger = logging.getLogger(__name__)
 )
 class QianbiSearcher(BaseSearcher):
     site_name = "qianbi"
-    priority = 3
+    priority = 10
+    BASE_URL = "https://www.23qb.com/"
     SEARCH_URL = "https://www.23qb.com/search.html"
 
     @classmethod
-    def _fetch_html(cls, keyword: str) -> str:
-        """
-        Fetch raw HTML from Qianbi's search page.
-
-        :param keyword: The search term to query on Qianbi.
-        :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 Qianbi search results into list of SearchResult.
-
-        :param html_str: Raw HTML string from Qianbi search results page.
-        :param limit: Maximum number of results to return, or None for all.
-        :return: List of SearchResult dicts.
-        """
         if html_str.find('<meta property="og:url"') != -1:
             return cls._parse_detail_html(html_str)
         return cls._parse_search_list_html(html_str, limit)
@@ -68,25 +54,53 @@ class QianbiSearcher(BaseSearcher):
         :return: A single-element list with the book's SearchResult.
         """
         doc = html.fromstring(html_str)
-        url = doc.xpath('//meta[@property="og:url"]/@content')
-        if not url:
+
+        book_url = cls._first_str(doc.xpath("//meta[@property='og:url']/@content"))
+        if not book_url:
             return []
 
-        # extract book_id via regex
-        m = re.search(r"/book/(\d+)/", url[0])
-        book_id = m.group(1) if m else ""
-        # title from <h1 class="page-title">
-        title = (doc.xpath('//h1[@class="page-title"]/text()') or [""])[0].strip()
-        author = (doc.xpath('//a[contains(@href,"/author/")]/@title') or [""])[
-            0
-        ].strip()
+        # 'https://www.23qb.com/book/9268/' -> "9268"
+        book_id = book_url.split("book/", 1)[-1].strip("/")
+
+        cover_rel = cls._first_str(
+            doc.xpath("//div[contains(@class,'novel-cover')]//img/@data-src")
+        ) or cls._first_str(
+            doc.xpath("//div[contains(@class,'novel-cover')]//img/@src")
+        )
+        cover_url = cls._abs_url(cover_rel) if cover_rel else ""
+
+        title = cls._first_str(doc.xpath("//h1[@class='page-title']/text()"))
+        author = cls._first_str(doc.xpath("//a[contains(@href, '/author/')]/@title"))
+
+        latest_chapter = (
+            cls._first_str(
+                doc.xpath(
+                    "//div[@class='module-row-info']//a[@class='module-row-text']/@title"
+                )
+            )
+            or "-"
+        )
+        update_date = (
+            cls._first_str(
+                doc.xpath("//div[@class='module-heading newchapter']/time/text()"),
+                replaces=[("更新时间：", "")],
+            )
+            or "-"
+        )
+
+        word_count = cls._first_str(doc.xpath("//span[contains(text(), '字')]/text()"))
 
         return [
             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=word_count,
                 priority=cls.priority,
             )
         ]
@@ -99,23 +113,38 @@ class QianbiSearcher(BaseSearcher):
         Parse a multi-item search result page.
 
         :param html_str: Raw HTML of the search-results page.
-        :param limit:    Maximum number of items to return, or None for all.
-        :return:         List of SearchResult.
+        :param limit: Maximum number of items to return, or None for all.
+        :return: List of SearchResult.
         """
         doc = html.fromstring(html_str)
         items = doc.xpath('//div[contains(@class,"module-search-item")]')
         results: list[SearchResult] = []
 
         for idx, item in enumerate(items):
+            href = cls._first_str(
+                item.xpath(".//div[@class='novel-info-header']/h3/a/@href")
+            )
+            if not href:
+                continue
+
             if limit is not None and idx >= limit:
                 break
-            # Title and book_id
-            link = item.xpath('.//div[@class="novel-info-header"]/h3/a')[0]
-            title = link.text_content().strip()
-            href = link.get("href", "").strip("/")
-            book_id = href.replace("book/", "").strip("/")
-            # Author is not present on the page
-            author = ""
+
+            # '/book/9138/' -> "9138"
+            book_id = href.rstrip("/").split("/")[-1]
+            book_url = cls._abs_url(href)
+
+            title = cls._first_str(
+                item.xpath(".//div[@class='novel-info-header']/h3/a//text()")
+            )
+
+            cover_rel = cls._first_str(
+                item.xpath(".//div[contains(@class,'module-item-pic')]//img/@data-src")
+            ) or cls._first_str(
+                item.xpath(".//div[contains(@class,'module-item-pic')]//img/@src")
+            )
+            cover_url = cls._abs_url(cover_rel) if cover_rel else ""
+
             # Compute priority
             prio = cls.priority + idx
 
@@ -123,8 +152,13 @@ class QianbiSearcher(BaseSearcher):
                 SearchResult(
                     site=cls.site_name,
                     book_id=book_id,
+                    book_url=book_url,
+                    cover_url=cover_url,
                     title=title,
-                    author=author,
+                    author="-",  # Author is not present on the page
+                    latest_chapter="-",
+                    update_date="-",
+                    word_count="-",
                     priority=prio,
                 )
             )

novel_downloader/core/searchers/quanben5.py

@@ -0,0 +1,144 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.searchers.quanben5
+----------------------------------------
+
+"""
+
+import json
+import logging
+import random
+import time
+
+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=["quanben5"],
+)
+class Quanben5Searcher(BaseSearcher):
+    site_name = "quanben5"
+    priority = 30
+    BASE_URL = "https://quanben5.com"
+    SEARCH_URL = "https://quanben5.com/"
+
+    STATIC_CHARS = "PXhw7UT1B0a9kQDKZsjIASmOezxYG4CHo5Jyfg2b8FLpEvRr3WtVnlqMidu6cN"
+
+    @classmethod
+    async def _fetch_html(cls, keyword: str) -> str:
+        t = str(int(time.time() * 1000))
+        uri_keyword = cls._quote(keyword)
+        b_raw = cls._base64(uri_keyword)
+        b = cls._quote(b_raw)
+
+        params = {
+            "c": "book",
+            "a": "search.json",
+            "callback": "search",
+            "t": t,
+            "keywords": uri_keyword,
+            "b": b,
+        }
+        full_url = cls._build_url(cls.SEARCH_URL, params)
+
+        headers = {
+            "Host": "quanben5.com",
+            "Referer": "https://quanben5.com/search.html",
+        }
+
+        try:
+            async with (await cls._http_get(full_url, headers=headers)) 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]:
+        # Unwrap JSONP: search({...});
+        prefix, suffix = "search(", ");"
+        json_str = (
+            html_str[len(prefix) : -len(suffix)]
+            if html_str.startswith(prefix) and html_str.endswith(suffix)
+            else html_str
+        )
+
+        try:
+            data = json.loads(json_str)
+        except json.JSONDecodeError:
+            return []
+
+        content_html = data.get("content", "")
+        if not content_html:
+            return []
+
+        doc = html.fromstring(content_html)
+        rows = doc.xpath('//div[@class="pic_txt_list"]')
+        results: list[SearchResult] = []
+
+        for idx, row in enumerate(rows):
+            href = cls._first_str(row.xpath(".//h3/a/@href"))
+            if not href:
+                continue
+
+            if limit is not None and idx >= limit:
+                break
+
+            # '/n/douposanqian/' -> "douposanqian"
+            book_id = href.rstrip("/").split("/")[-1]
+            book_url = cls._abs_url(href)
+
+            cover_rel = cls._first_str(row.xpath(".//div[@class='pic']//img/@src"))
+            cover_url = cls._abs_url(cover_rel) if cover_rel else ""
+
+            title = "".join(
+                t.strip()
+                for t in row.xpath(".//h3/a/span[@class='name']//text()")
+                if t and t.strip()
+            )
+
+            author = cls._first_str(
+                row.xpath(".//p[@class='info']//span[contains(@class,'author')]/text()")
+            )
+
+            # Bump priority by result index
+            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="-",
+                    update_date="-",
+                    word_count="-",
+                    priority=prio,
+                )
+            )
+        return results
+
+    @classmethod
+    def _base64(cls, s: str) -> str:
+        out = []
+        for ch in s:
+            idx = cls.STATIC_CHARS.find(ch)
+            code = cls.STATIC_CHARS[(idx + 3) % 62] if idx != -1 else ch
+            n1 = int(random.random() * 62)
+            n2 = int(random.random() * 62)
+            out.append(cls.STATIC_CHARS[n1])
+            out.append(code)
+            out.append(cls.STATIC_CHARS[n2])
+        return "".join(out)

novel_downloader/core/searchers/registry.py

@@ -7,9 +7,12 @@ novel_downloader.core.searchers.registry
 
 __all__ = ["register_searcher", "search"]
 
+import asyncio
 from collections.abc import Callable, Sequence
 from typing import TypeVar
 
+import aiohttp
+
 from novel_downloader.core.searchers.base import BaseSearcher
 from novel_downloader.models import SearchResult
 
@@ -33,31 +36,44 @@ def register_searcher(
     return decorator
 
 
-def search(
+async def search(
     keyword: str,
     sites: Sequence[str] | None = None,
     limit: int | None = None,
     per_site_limit: int = 5,
+    timeout: float = 5.0,
 ) -> list[SearchResult]:
     """
     Perform a search for the given keyword across one or more registered sites,
     then aggregate and sort the results by their `priority` value.
 
     :param keyword: The search term or keyword to query.
-    :param sites:   An optional sequence of site keys to limit which searchers.
-    :param limit:   Maximum total number of results to return; if None, return all.
+    :param sites: An optional sequence of site keys to limit which searchers.
+    :param limit: Maximum total number of results to return; if None, return all.
     :param per_site_limit: Maximum number of search results per site.
-    :return:        A flat list of `SearchResult` objects.
+    :param timeout: Per-request time budget (seconds)
+    :return: A flat list of `SearchResult` objects.
     """
     keys = list(sites or _SEARCHER_REGISTRY.keys())
     to_call = {_SEARCHER_REGISTRY[key] for key in keys if key in _SEARCHER_REGISTRY}
 
+    site_timeout = aiohttp.ClientTimeout(total=timeout)
+
     results: list[SearchResult] = []
-    for cls in to_call:
-        try:
-            results.extend(cls.search(keyword, limit=per_site_limit))
-        except Exception:
+    async with aiohttp.ClientSession(timeout=site_timeout) as session:
+        # Give all searchers the same session
+        for cls in to_call:
+            cls.configure(session)
+
+        # Kick off all sites in parallel
+        coros = [cls.search(keyword, limit=per_site_limit) for cls in to_call]
+        site_lists = await asyncio.gather(*coros, return_exceptions=True)
+
+    # Collect successful results; skip failures
+    for item in site_lists:
+        if isinstance(item, Exception | BaseException):
             continue
+        results.extend(item)
 
     results.sort(key=lambda res: res["priority"])
     return results[:limit] if limit is not None else results

novel_downloader/core/searchers/shuhaige.py

@@ -0,0 +1,124 @@
+#!/usr/bin/env python3
+"""
+novel_downloader.core.searchers.shuhaige
+----------------------------------------
+
+"""
+
+import logging
+import time
+
+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=["shuhaige"],
+)
+class ShuhaigeSearcher(BaseSearcher):
+    site_name = "shuhaige"
+    priority = 30
+    BASE_URL = "https://www.shuhaige.net"
+    SEARCH_URL = "https://www.shuhaige.net/search.html"
+
+    @classmethod
+    async def _fetch_html(cls, keyword: str) -> str:
+        data = {
+            "searchtype": "all",
+            "searchkey": keyword,
+        }
+        ts = int(time.time())
+        # baidu cookie format: f"Hm_lpvt_{site_id}={timestamp}"
+        cookie_str = (
+            f"Hm_lpvt_3094b20ed277f38e8f9ac2b2b29d6263={ts}; "
+            f"Hm_lpvt_c3da01855456ad902664af23cc3254cb={ts}"
+        )
+        headers = {
+            "Origin": "https://www.shuhaige.net",
+            "Referer": "https://www.shuhaige.net/",
+            "Cookie": cookie_str,
+        }
+        try:
+            async with (
+                await cls._http_post(cls.SEARCH_URL, data=data, headers=headers)
+            ) 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="sitembox"]/dl')
+        results: list[SearchResult] = []
+
+        for idx, row in enumerate(rows):
+            href = cls._first_str(row.xpath("./dt/a[1]/@href")) or cls._first_str(
+                row.xpath("./dd/h3/a[1]/@href")
+            )
+            if not href:
+                continue
+
+            if limit is not None and idx >= limit:
+                break
+
+            book_id = href.strip("/").split("/")[0]
+            book_url = cls._abs_url(href)
+
+            title = cls._first_str(row.xpath("./dd/h3/a[1]//text()")) or cls._first_str(
+                row.xpath("./dt/a[1]/img[1]/@alt")
+            )
+
+            cover_rel = cls._first_str(row.xpath("./dt/a[1]/img[1]/@src"))
+            cover_url = cls._abs_url(cover_rel) if cover_rel else ""
+
+            author = (
+                cls._first_str(row.xpath("./dd[@class='book_other'][1]/span[1]/text()"))
+                or "-"
+            )
+            word_count = (
+                cls._first_str(row.xpath("./dd[@class='book_other'][1]/span[4]/text()"))
+                or "-"
+            )
+
+            latest_chapter = (
+                cls._first_str(
+                    row.xpath("./dd[@class='book_other'][last()]/a[1]//text()")
+                )
+                or "-"
+            )
+            update_date = (
+                cls._first_str(
+                    row.xpath("./dd[@class='book_other'][last()]/span[1]//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=author,
+                    latest_chapter=latest_chapter,
+                    update_date=update_date,
+                    word_count=word_count,
+                    priority=prio,
+                )
+            )
+        return results