Merge pull request #2674 from InfinityPacer/dev

app/chain/site.py

@@ -205,7 +205,7 @@ class SiteChain(ChainBase):
             logger.error(f"获取站点页面失败：{url}")
             return favicon_url, None
         html = etree.HTML(html_text)
-        if html:
+        if StringUtils.is_valid_html_element(html):
             fav_link = html.xpath('//head/link[contains(@rel, "icon")]/@href')
             if fav_link:
                 favicon_url = urljoin(url, fav_link[0])

app/helper/rss.py

@@ -363,7 +363,7 @@ class RssHelper:
                     return "", f"获取RSS链接失败：无法连接 {url} "
             # 解析HTML
             html = etree.HTML(html_text)
-            if html:
+            if StringUtils.is_valid_html_element(html):
                 rss_link = html.xpath(site_conf.get("xpath"))
                 if rss_link:
                     return str(rss_link[-1]), ""

app/modules/indexer/parser/discuz.py

@@ -34,7 +34,7 @@ class DiscuzUserInfo(SiteParserBase):
         :return:
         """
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return None
 
         # 用户等级
@@ -77,7 +77,7 @@ class DiscuzUserInfo(SiteParserBase):
         :return: 下页地址
         """
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return None
 
         size_col = 3

app/modules/indexer/parser/file_list.py

@@ -82,7 +82,7 @@ class FileListSiteUserInfo(SiteParserBase):
         :return: 下页地址
         """
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return None
 
         size_col = 6

app/modules/indexer/parser/gazelle.py

@@ -65,7 +65,7 @@ class GazelleSiteUserInfo(SiteParserBase):
         :return:
         """
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return None
 
         # 用户等级
@@ -95,7 +95,7 @@ class GazelleSiteUserInfo(SiteParserBase):
         :return: 下页地址
         """
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return None
 
         size_col = 3

app/modules/indexer/parser/ipt_project.py

@@ -39,7 +39,7 @@ class IptSiteUserInfo(SiteParserBase):
 
     def _parse_user_detail_info(self, html_text: str):
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return
 
         user_levels_text = html.xpath('//tr/th[text()="Class"]/following-sibling::td[1]/text()')
@@ -53,7 +53,7 @@ class IptSiteUserInfo(SiteParserBase):
 
     def _parse_user_torrent_seeding_info(self, html_text: str, multi_page: bool = False) -> Optional[str]:
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return
         # seeding start
         seeding_end_pos = 3

app/modules/indexer/parser/nexus_hhanclub.py

@@ -42,7 +42,7 @@ class NexusHhanclubSiteUserInfo(NexusPhpSiteUserInfo):
         super()._parse_user_detail_info(html_text)
 
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return
         # 加入时间
         join_at_text = html.xpath('//*[@id="mainContent"]/div/div[2]/div[4]/div[3]/span[2]/text()[1]')

app/modules/indexer/parser/nexus_php.py

@@ -34,7 +34,7 @@ class NexusPhpSiteUserInfo(SiteParserBase):
         :return:
         """
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return
 
         message_labels = html.xpath('//a[@href="messages.php"]/..')
@@ -61,7 +61,7 @@ class NexusPhpSiteUserInfo(SiteParserBase):
         self._parse_message_unread(html_text)
 
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return
 
         ret = html.xpath(f'//a[contains(@href, "userdetails") and contains(@href, "{self.userid}")]//b//text()')
@@ -128,7 +128,7 @@ class NexusPhpSiteUserInfo(SiteParserBase):
         :param html:
         :return:
         """
-        if html:
+        if StringUtils.is_valid_html_element(html):
             gold, silver, copper = None, None, None
 
             golds = html.xpath('//span[@class = "ucoin-symbol ucoin-gold"]//text()')
@@ -155,7 +155,7 @@ class NexusPhpSiteUserInfo(SiteParserBase):
         :return: 下页地址
         """
         html = etree.HTML(str(html_text).replace(r'\/', '/'))
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return None
 
         # 首页存在扩展链接，使用扩展链接
@@ -223,7 +223,7 @@ class NexusPhpSiteUserInfo(SiteParserBase):
         :return:
         """
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return
 
         self._get_user_level(html)
@@ -340,7 +340,7 @@ class NexusPhpSiteUserInfo(SiteParserBase):
 
     def _parse_message_unread_links(self, html_text: str, msg_links: list) -> Optional[str]:
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return None
 
         message_links = html.xpath('//tr[not(./td/img[@alt="Read"])]/td/a[contains(@href, "viewmessage")]/@href')
@@ -355,7 +355,7 @@ class NexusPhpSiteUserInfo(SiteParserBase):
 
     def _parse_message_content(self, html_text):
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return None, None, None
         # 标题
         message_head_text = None

app/modules/indexer/parser/small_horse.py

@@ -63,7 +63,7 @@ class SmallHorseSiteUserInfo(SiteParserBase):
          :return: 下页地址
          """
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return None
 
         size_col = 6

app/modules/indexer/parser/torrent_leech.py

@@ -67,7 +67,7 @@ class TorrentLeechSiteUserInfo(SiteParserBase):
         :return: 下页地址
         """
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return None
 
         size_col = 2

app/modules/indexer/parser/unit3d.py

@@ -40,7 +40,7 @@ class Unit3dSiteUserInfo(SiteParserBase):
         :return:
         """
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return None
 
         # 用户等级
@@ -64,7 +64,7 @@ class Unit3dSiteUserInfo(SiteParserBase):
         :return: 下页地址
         """
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return None
 
         size_col = 9

app/utils/site.py

@@ -1,5 +1,7 @@
 from lxml import etree
 
+from app.utils.string import StringUtils
+
 
 class SiteUtils:
 
@@ -11,7 +13,7 @@ class SiteUtils:
         :return:
         """
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return False
         # 存在明显的密码输入框，说明未登录
         if html.xpath("//input[@type='password']"):
@@ -39,7 +41,7 @@ class SiteUtils:
         :return True已签到 False未签到
         """
         html = etree.HTML(html_text)
-        if not html:
+        if not StringUtils.is_valid_html_element(html):
             return False
         # 站点签到支持的识别XPATH
         xpaths = [

app/utils/string.py

@@ -795,3 +795,13 @@ class StringUtils:
         :return: 如果输入值不是 None，返回去除空白字符后的字符串，否则返回 None
         """
         return value.strip() if value is not None else None
+
+    @staticmethod
+    def is_valid_html_element(elem) -> bool:
+        """
+        检查elem是否为有效的HTML元素。元素必须为非None并且具有非零长度。
+
+        :param elem: 要检查的HTML元素
+        :return: 如果elem有效（非None且长度大于0），返回True；否则返回False
+        """
+        return elem is not None and len(elem) > 0