fix hhanclub数据统计

2023-08-30 14:51:55 +08:00
parent f8221bb526
commit 16289d86b6
3 changed files with 71 additions and 18 deletions
--- a/app/plugins/sitestatistic/siteuserinfo/nexus_hhanclub.py
+++ b/app/plugins/sitestatistic/siteuserinfo/nexus_hhanclub.py
@ -0,0 +1,60 @@
+# -*- coding: utf-8 -*-
+import re
+
+from lxml import etree
+
+from app.plugins.sitestatistic.siteuserinfo import SITE_BASE_ORDER, SiteSchema
+from app.plugins.sitestatistic.siteuserinfo.nexus_php import NexusPhpSiteUserInfo
+from app.utils.string import StringUtils
+
+
+class NexusHhanclubSiteUserInfo(NexusPhpSiteUserInfo):
+    schema = SiteSchema.NexusHhanclub
+    order = SITE_BASE_ORDER + 20
+
+    @classmethod
+    def match(cls, html_text: str) -> bool:
+        return 'hhanclub.top' in html_text
+
+    def _parse_user_traffic_info(self, html_text):
+        super()._parse_user_traffic_info(html_text)
+
+        html_text = self._prepare_html_text(html_text)
+        html = etree.HTML(html_text)
+
+        # 上传、下载、分享率
+        upload_match = re.search(r"[_<>/a-zA-Z-=\"'\s#;]+([\d,.\s]+[KMGTPI]*B)",
+                                 html.xpath('//*[@id="user-info-panel"]/div[2]/div[2]/div[4]/text()')[0])
+        download_match = re.search(r"[_<>/a-zA-Z-=\"'\s#;]+([\d,.\s]+[KMGTPI]*B)",
+                                   html.xpath('//*[@id="user-info-panel"]/div[2]/div[2]/div[5]/text()')[0])
+        ratio_match = re.search(r"分享率][:：_<>/a-zA-Z-=\"'\s#;]+([\d,.\s]+)",
+                                html.xpath('//*[@id="user-info-panel"]/div[2]/div[1]/div[1]/div/text()')[0])
+
+        # 计算分享率
+        self.upload = StringUtils.num_filesize(upload_match.group(1).strip()) if upload_match else 0
+        self.download = StringUtils.num_filesize(download_match.group(1).strip()) if download_match else 0
+        # 优先使用页面上的分享率
+        calc_ratio = 0.0 if self.download <= 0.0 else round(self.upload / self.download, 3)
+        self.ratio = StringUtils.str_float(ratio_match.group(1)) if (
+                ratio_match and ratio_match.group(1).strip()) else calc_ratio
+
+    def _parse_user_detail_info(self, html_text: str):
+        """
+        解析用户额外信息，加入时间，等级
+        :param html_text:
+        :return:
+        """
+        super()._parse_user_detail_info(html_text)
+
+        html = etree.HTML(html_text)
+        if not html:
+            return
+        # 加入时间
+        join_at_text = html.xpath('//*[@id="mainContent"]/div/div[2]/div[4]/div[3]/span[2]/text()[1]')
+        if join_at_text:
+            self.join_at = StringUtils.unify_datetime_str(join_at_text[0].split(' (')[0].strip())
+
+    def _get_user_level(self, html):
+        super()._get_user_level(html)
+
+        self.user_level = html.xpath('//*[@id="mainContent"]/div/div[2]/div[2]/div[4]/img/@title')[0]