cookies

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/MarsCodeWorkspaceAppSettings.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="com.codeverse.userSettings.MarscodeWorkspaceAppSettingsState">
+    <option name="ckgOperationStatus" value="SUCCESS" />
+    <option name="progress" value="1.0" />
+  </component>
+</project>

.idea/SearchCompany.iml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/.venv" />
+    </content>
+    <orderEntry type="jdk" jdkName="Python 3.13 (SearchCompany)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.13 (SearchCompany)" />
+  </component>
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/SearchCompany.iml" filepath="$PROJECT_DIR$/.idea/SearchCompany.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

Readme.md

@@ -0,0 +1 @@
+pip install -r requirements.txt

company/qcc.py

@@ -0,0 +1,344 @@
+# qcc.py
+import json
+import re
+import os
+from playwright.sync_api import sync_playwright
+import argparse
+
+
+def clean_text(text):
+    """
+    清理文本内容，去除多余空白字符
+    """
+    if not text:
+        return ""
+    # 替换多个空白字符为单个空格，并去除首尾空白
+    return re.sub(r'\s+', ' ', text.replace('\r', '').replace('\n', '').replace('\t', '')).strip()
+
+
+class QCCParser:
+    def __init__(self, page):
+        self.page = page
+        self.company_data = {}
+
+    def init_table(self):
+        """
+        初始化表格元素
+        """
+        # 等待页面加载完成
+        self.page.wait_for_load_state('networkidle')
+
+        # 查找企业信息容器
+        cominfo_normal = self.page.query_selector("div.cominfo-normal")
+        if not cominfo_normal:
+            print("未找到企业信息容器")
+            return False
+
+        # 查找企业信息表格
+        self.table = cominfo_normal.query_selector("table.ntable")
+        if not self.table:
+            print("未找到企业信息表格")
+            return False
+
+        return True
+
+    def get_optimized_value(self, title):
+        """
+        根据标题获取对应的值
+        """
+        # 查找所有表头单元格
+        header_cells = self.table.query_selector_all("td.tb")
+        value = None
+
+        for header in header_cells:
+            if clean_text(header.text_content()).find(title) != -1:
+                value_cell = header.query_selector("+ td")
+                if value_cell:
+                    # 尝试从copy-value类中获取值
+                    copy_value = value_cell.query_selector(".copy-value")
+                    if copy_value:
+                        value = clean_text(copy_value.text_content())
+                    else:
+                        value = clean_text(value_cell.text_content())
+                break
+
+        return value
+
+    def get_legal_representative(self):
+        """
+        获取法定代表人
+        """
+        # 尝试基本方法获取
+        basic_value = self.get_optimized_value("法定代表人") or self.get_optimized_value("法人")
+        if basic_value and basic_value.strip():
+            # 移除"关联企业 X"等附加信息
+            return re.sub(r'\s*关联企业\s*\d+$', '', basic_value).strip()
+
+        # 查找法定代表人表头
+        header_cell = None
+        for cell in self.table.query_selector_all("td.tb"):
+            if clean_text(cell.text_content()).find("法定代表人") != -1:
+                header_cell = cell
+                break
+
+        if not header_cell:
+            return None
+
+        value_cell = header_cell.query_selector("+ td")
+        if not value_cell:
+            return None
+
+        # 查找包含法定代表人姓名的链接
+        name_links = value_cell.query_selector_all('a[target="_blank"]')
+        for link in name_links:
+            name = clean_text(link.text_content())
+            # 确保不是空值且不包含非姓名文本
+            if name and "关联企业" not in name and "复制" not in name:
+                return name
+
+        # 备选方案：查找第一个链接
+        first_link = value_cell.query_selector("a")
+        if first_link:
+            name = clean_text(first_link.text_content())
+            return re.sub(r'\s*关联企业\s*\d+$', '', name).strip()
+
+        # 最后备选方案：直接提取文本
+        copy_value = value_cell.query_selector(".copy-value")
+        if copy_value:
+            name = clean_text(copy_value.text_content())
+            return re.sub(r'\s*关联企业\s*\d+$', '', name).strip()
+
+        raw_text = clean_text(value_cell.text_content())
+        return re.sub(r'\s*关联企业\s*\d+$', '', raw_text).strip()
+
+    def get_unified_social_credit_code(self):
+        """
+        获取统一社会信用代码
+        """
+        return (self.get_optimized_value("统一社会信用代码") or
+                self.get_optimized_value("信用代码"))
+
+    def get_business_registration_no(self):
+        """
+        获取工商注册号
+        """
+        return (self.get_optimized_value("工商注册号") or
+                self.get_optimized_value("注册号"))
+
+    def get_organization_code(self):
+        """
+        获取组织机构代码
+        """
+        return self.get_optimized_value("组织机构代码")
+
+    def get_taxpayer_id(self):
+        """
+        获取纳税人识别号
+        """
+        return (self.get_optimized_value("纳税人识别号") or
+                self.get_unified_social_credit_code())
+
+    def get_insurance_number(self):
+        """
+        获取参保人数
+        """
+        # 查找参保人数表头
+        header_cell = None
+        for cell in self.table.query_selector_all("td.tb"):
+            if clean_text(cell.text_content()).find("参保人数") != -1:
+                header_cell = cell
+                break
+
+        if not header_cell:
+            return None
+
+        value_cell = header_cell.query_selector("+ td")
+        if not value_cell:
+            return None
+
+        # 提取参保人数数字
+        number_span = value_cell.query_selector("span")
+        number = clean_text(number_span.text_content()) if number_span else None
+
+        # 提取年报年份
+        report_link = value_cell.query_selector("a.m-l-r-10")
+        report_year = clean_text(report_link.text_content()) if report_link else ""
+
+        # 组合结果
+        return f"{number}人 {report_year}" if number else None
+
+    def get_phone_number(self):
+        """
+        获取联系电话
+        """
+        # 查找联系信息容器
+        contact_info = self.page.query_selector("div.contact-info")
+        if not contact_info:
+            return None
+
+        # 查找右侧信息区域
+        right_part = contact_info.query_selector("div.main-part-item.right")
+        if not right_part:
+            return None
+
+        # 查找包含电话的行
+        rows = right_part.query_selector_all("div.rline")
+        phone_row = None
+        for row in rows:
+            if clean_text(row.text_content()).find("电话：") != -1:
+                phone_row = row
+                break
+
+        if not phone_row:
+            return None
+
+        # 提取电话号码
+        spans = phone_row.query_selector_all("span.need-copy-field")
+        phone_span = None
+        for span in spans:
+            if clean_text(span.text_content()).find("电话：") == -1:
+                phone_span = span
+                break
+
+        return clean_text(phone_span.text_content()) if phone_span else None
+
+    def get_approval_date(self):
+        """
+        获取核准日期
+        """
+        return (self.get_optimized_value("核准日期") or
+                self.get_optimized_value("成立日期"))
+
+    def parse_company_info(self):
+        """
+        解析公司信息主方法
+        """
+        if not self.init_table():
+            return None
+
+        self.company_data = {
+            "企业名称": (self.get_optimized_value("企业名称") or
+                         self.get_optimized_value("公司名称")),
+            "统一社会信用代码": self.get_unified_social_credit_code(),
+            "法定代表人": self.get_legal_representative(),
+            "经营状态": self.get_optimized_value("登记状态"),
+            "成立日期": self.get_optimized_value("成立日期"),
+            "行政区划": self.get_optimized_value("行政区划"),
+            "注册资本": self.get_optimized_value("注册资本"),
+            "实缴资本": self.get_optimized_value("实缴资本"),
+            "企业类型": self.get_optimized_value("企业类型"),
+            "所属行业": self.get_optimized_value("国标行业"),
+            "工商注册号": self.get_business_registration_no(),
+            "组织机构代码": self.get_organization_code(),
+            "纳税人识别号": self.get_taxpayer_id(),
+            "纳税人资质": self.get_optimized_value("纳税人资质"),
+            "营业期限": self.get_optimized_value("营业期限"),
+            "核准日期": self.get_approval_date(),
+            "参保人数": self.get_insurance_number(),
+            "电话": self.get_phone_number(),
+            "登记机关": self.get_optimized_value("登记机关"),
+            "曾用名": self.get_optimized_value("曾用名"),
+            "注册地址": self.get_optimized_value("注册地址"),
+            "经营范围": self.get_optimized_value("经营范围"),
+        }
+
+        return self.company_data
+
+
+def load_cookies(context, cookie_file):
+    """
+    从文件加载cookies
+    """
+    if os.path.exists(cookie_file):
+        with open(cookie_file, 'r') as f:
+            cookies = json.load(f)
+            context.add_cookies(cookies)
+        print("已加载本地cookies")
+        return True
+    return False
+
+
+def save_cookies(context, cookie_file):
+    """
+    保存cookies到文件
+    """
+    cookies = context.cookies()
+    with open(cookie_file, 'w') as f:
+        json.dump(cookies, f)
+    print("已保存cookies到文件")
+
+
+def wait_for_login(page, cookie_file):
+    """
+    等待用户扫码登录
+    """
+    print("检测到需要登录，请使用手机扫码登录...")
+    print("登录成功后将自动跳转到目标页面")
+
+    # 等待页面跳转到非登录页面
+    page.wait_for_url("**/weblogin", timeout=3000)
+    page.wait_for_url(lambda url: "weblogin" not in url, timeout=120000)
+
+    # 保存登录后的cookies
+    save_cookies(page.context, cookie_file)
+    print("登录成功，已保存cookies")
+
+
+def main():
+    parser = argparse.ArgumentParser(description='解析企查查公司信息')
+    parser.add_argument('url', help='企查查公司页面URL')
+    parser.add_argument('--headless', action='store_true', help='无头模式运行')
+    parser.add_argument('--cookie-file', default='qcc_cookies.txt', help='cookies文件路径')
+
+    args = parser.parse_args()
+
+    with sync_playwright() as p:
+        # 启动浏览器
+        browser = p.chromium.launch(headless=args.headless)
+        context = browser.new_context()
+        page = context.new_page()
+
+        try:
+            # 尝试加载本地保存的cookies
+            if load_cookies(context, args.cookie_file):
+                print("使用已保存的登录信息")
+
+            # 访问指定URL
+            page.goto(args.url)
+
+            # 检查是否跳转到了登录页面
+            if "weblogin" in page.url:
+                wait_for_login(page, args.cookie_file)
+            else:
+                print("已登录或无需登录")
+
+            # 重新访问目标URL（确保页面正确加载）
+            page.goto(args.url)
+
+            # 创建解析器并解析信息
+            parser = QCCParser(page)
+            company_info = parser.parse_company_info()
+
+            if company_info:
+                # 格式化输出JSON
+                print(json.dumps(company_info, ensure_ascii=False, indent=2))
+            else:
+                print("未能获取公司信息")
+
+        except Exception as e:
+            print(f"发生错误: {e}")
+        finally:
+            browser.close()
+
+
+if __name__ == "__main__":
+    main()
+    # python qcc.py "https://www.qcc.com/firm/50b0e3189f2eb2b20304b255669ce1a1.html"
+# # 首次运行需要扫码登录
+# python qcc.py "https://www.qcc.com/firm/公司URL"
+#
+# # 后续运行将自动使用已保存的登录信息
+# python qcc.py "https://www.qcc.com/firm/公司URL"
+#
+# # 指定自定义cookies文件
+# python qcc.py --cookie-file my_cookies.txt "https://www.qcc.com/firm/公司URL"

company/youhou.js

@@ -0,0 +1,831 @@
+// ==UserScript==
+// @name         爱企查&企查查等
+// @namespace    http://tampermonkey.net/
+// @version      0.2
+// @description  在页面右下角添加工具按钮，支持复制源码和解析公司信息
+// @author       You
+// @match        https://www.qcc.com/firm/*
+// @match        https://aiqicha.baidu.com/company_detail_*
+// @grant        none
+// ==/UserScript==
+
+(function () {
+  "use strict";
+
+  // 工具类 - 存放通用函数
+  class ToolUtils {
+    static cleanText(text) {
+      return text
+        .replace(/\s+/g, " ")
+        .replace(/[\r\n\t]/g, "")
+        .trim();
+    }
+
+    static extractText(doc, selectors) {
+      for (const selector of selectors) {
+        const element = doc.querySelector(selector);
+        if (element && element.textContent.trim()) {
+          return element.textContent.trim();
+        }
+      }
+      return "";
+    }
+
+    static copyToClipboard(content, successMessage) {
+      const textarea = document.createElement("textarea");
+      textarea.value = content;
+      textarea.style.position = "fixed";
+      textarea.style.top = "0";
+      textarea.style.left = "0";
+      textarea.style.width = "1px";
+      textarea.style.height = "1px";
+      textarea.style.opacity = "0";
+
+      document.body.appendChild(textarea);
+      textarea.select();
+      document.execCommand("copy");
+      document.body.removeChild(textarea);
+
+      if (successMessage) {
+        this.showAutoCloseMessage(successMessage, "success");
+
+      }
+    }
+
+    static showAutoCloseMessage(message, type = "info") {
+      // 创建一个自动关闭的提示框替代 alert
+      const alertBox = document.createElement("div");
+      alertBox.textContent = message;
+      alertBox.style.position = "fixed";
+      alertBox.style.top = "50%";
+      alertBox.style.left = "50%";
+      alertBox.style.transform = "translate(-50%, -50%)";
+
+      // 根据消息类型设置不同颜色
+      if (type === "success") {
+        alertBox.style.backgroundColor = "#52c41a";
+      } else if (type === "error") {
+        alertBox.style.backgroundColor = "#f5222d";
+      } else {
+        alertBox.style.backgroundColor = "#1890ff";
+      }
+
+      alertBox.style.color = "white";
+      alertBox.style.padding = "10px 20px";
+      alertBox.style.borderRadius = "4px";
+      alertBox.style.zIndex = "10001";
+      alertBox.style.boxShadow = "0 2px 8px rgba(0,0,0,0.15)";
+      alertBox.style.transition = "opacity 0.3s";
+
+      document.body.appendChild(alertBox);
+
+      // 2秒后自动关闭
+      setTimeout(() => {
+        if (document.body.contains(alertBox)) {
+          // 添加淡出效果
+          alertBox.style.opacity = "0";
+          // 真正移除元素
+          setTimeout(() => {
+            if (document.body.contains(alertBox)) {
+              document.body.removeChild(alertBox);
+            }
+          }, 300);
+        }
+      }, 2000);
+    }
+
+    static showResult(data) {
+      const modal = document.createElement("div");
+      modal.style.position = "fixed";
+      modal.style.top = "50%";
+      modal.style.left = "50%";
+      modal.style.transform = "translate(-50%, -50%)";
+      modal.style.width = "600px";
+      modal.style.maxHeight = "80vh";
+      modal.style.overflowY = "auto";
+      modal.style.backgroundColor = "white";
+      modal.style.padding = "20px";
+      modal.style.boxShadow = "0 0 10px rgba(0,0,0,0.3)";
+      modal.style.zIndex = "10000";
+
+      const pre = document.createElement("pre");
+      pre.textContent = JSON.stringify(data, null, 2);
+      pre.style.whiteSpace = "pre-wrap";
+      pre.style.wordWrap = "break-word";
+
+      const copyBtn = document.createElement("button");
+      copyBtn.textContent = "复制JSON";
+      copyBtn.style.marginTop = "10px";
+      copyBtn.style.padding = "8px 16px";
+      copyBtn.style.backgroundColor = "#52c41a";
+      copyBtn.style.color = "white";
+      copyBtn.style.border = "none";
+      copyBtn.style.borderRadius = "4px";
+      copyBtn.style.cursor = "pointer";
+
+      copyBtn.addEventListener("click", () => {
+        navigator.clipboard
+          .writeText(JSON.stringify(data, null, 2))
+          .then(() => this.showAutoCloseMessage("已复制到剪贴板", "success"))
+          .catch((err) => alert("复制失败: " + err));
+      });
+
+      const closeBtn = document.createElement("button");
+      closeBtn.textContent = "关闭";
+      closeBtn.style.marginLeft = "10px";
+      closeBtn.style.marginTop = "10px";
+      closeBtn.style.padding = "8px 16px";
+      closeBtn.style.backgroundColor = "#f5222d";
+      closeBtn.style.color = "white";
+      closeBtn.style.border = "none";
+      closeBtn.style.borderRadius = "4px";
+      closeBtn.style.cursor = "pointer";
+
+      closeBtn.addEventListener("click", () => {
+        document.body.removeChild(modal);
+      });
+
+      modal.innerHTML = '<h2 style="margin-top: 0;">企业信息解析结果</h2>';
+      modal.appendChild(pre);
+      modal.appendChild(document.createElement("br"));
+      modal.appendChild(copyBtn);
+      modal.appendChild(closeBtn);
+
+      document.body.appendChild(modal);
+      // // Automatically close the modal after 2 seconds
+      // setTimeout(() => {
+      //   if (document.body.contains(modal)) {
+      //     document.body.removeChild(modal);
+      //   }
+      // }, 2000);
+    }
+  }
+
+  // 爱企查解析类
+  class AiQiChaParser {
+    getPhoneNumber() {
+      // 查找电话信息容器
+      const phoneContainer = document.querySelector(
+        "div.business-info div.telphone-lists-wrap"
+      );
+      if (!phoneContainer) return "未找到电话信息";
+
+      // 查找包含电话号码的元素
+      const phoneElement = phoneContainer.querySelector("span.copy-box span");
+      if (!phoneElement) return "未找到电话号码";
+
+      return ToolUtils.cleanText(phoneElement.textContent);
+    }
+    constructor() {
+      this.table = null;
+    }
+
+    // 初始化表格
+    initTable() {
+      this.table = document.querySelector("table.zx-detail-basic-table");
+      if (!this.table) {
+        alert("未找到企业信息表格");
+        return false;
+      }
+      return true;
+    }
+
+    // 获取优化后的值
+    getOptimizedValue(title) {
+      const cells = Array.from(this.table.querySelectorAll("td"));
+      const titleCell = cells.find(
+        (cell) => ToolUtils.cleanText(cell.textContent) === title
+      );
+
+      if (!titleCell) return null;
+
+      let valueCell = titleCell.nextElementSibling;
+      if (!valueCell) return null;
+
+      const valueElement =
+        valueCell.querySelector(".enter-bg-ele") ||
+        valueCell.querySelector(".addr-enter-bg-ele") ||
+        valueCell;
+
+      return ToolUtils.cleanText(valueElement.textContent);
+    }
+
+    // 获取法定代表人
+    getLegalRepresentative() {
+      const legalElements = Array.from(
+        this.table.querySelectorAll("td")
+      ).filter((td) => ToolUtils.cleanText(td.textContent) === "法定代表人");
+
+      if (legalElements.length > 0) {
+        const valueCell = legalElements[0].nextElementSibling;
+        if (valueCell && valueCell.classList.contains("image-text-content")) {
+          const nameElement = valueCell.querySelector(".person-name-warp a");
+          if (nameElement) {
+            return ToolUtils.cleanText(nameElement.textContent);
+          }
+          return ToolUtils.cleanText(valueCell.textContent);
+        }
+      }
+
+      const titleElements = Array.from(
+        this.table.querySelectorAll("td")
+      ).filter((td) => td.textContent.includes("法定代表人"));
+
+      if (titleElements.length > 0 && titleElements[0].nextElementSibling) {
+        const valueCell = titleElements[0].nextElementSibling;
+        return ToolUtils.cleanText(valueCell.textContent);
+      }
+
+      return null;
+    }
+
+    // 获取统一社会信用代码
+    getUnifiedSocialCreditCode() {
+      const codeElements = Array.from(this.table.querySelectorAll("td")).filter(
+        (td) => {
+          return (
+            td.textContent.includes("统一社会信用代码") &&
+            td.nextElementSibling &&
+            td.nextElementSibling.classList.contains("table-regCapital-lable")
+          );
+        }
+      );
+
+      if (codeElements.length > 0) {
+        const valueCell = codeElements[0].nextElementSibling;
+        const rawValue =
+          valueCell.querySelector(".enter-bg-ele")?.textContent ||
+          valueCell.textContent;
+        return ToolUtils.cleanText(rawValue);
+      }
+
+      const taxElements = Array.from(this.table.querySelectorAll("td")).filter(
+        (td) => td.textContent.includes("纳税人识别号")
+      );
+
+      if (taxElements.length > 0 && taxElements[0].nextElementSibling) {
+        const valueCell = taxElements[0].nextElementSibling;
+        const rawValue =
+          valueCell.querySelector(".enter-bg-ele")?.textContent ||
+          valueCell.textContent;
+        return ToolUtils.cleanText(rawValue);
+      }
+
+      return null;
+    }
+
+    // 获取工商注册号
+    getBusinessRegistrationNo() {
+      const regElements = Array.from(this.table.querySelectorAll("td")).filter(
+        (td) => ToolUtils.cleanText(td.textContent).includes("工商注册号")
+      );
+
+      if (regElements.length > 0 && regElements[0].nextElementSibling) {
+        const valueCell = regElements[0].nextElementSibling;
+        const rawValue =
+          valueCell.querySelector(".enter-bg-ele")?.textContent ||
+          valueCell.textContent;
+        return ToolUtils.cleanText(rawValue);
+      }
+
+      return null;
+    }
+
+    // 获取组织机构代码
+    getOrganizationCode() {
+      const orgCodeElements = Array.from(
+        this.table.querySelectorAll(".poptip-wrap-org-no")
+      ).filter((el) => el.textContent.includes("组织机构代码"));
+
+      if (orgCodeElements.length > 0) {
+        const valueCell = orgCodeElements[0].closest("td").nextElementSibling;
+        if (valueCell && valueCell.classList.contains("enter-bg")) {
+          const rawValue =
+            valueCell.querySelector(".enter-bg-ele")?.textContent ||
+            valueCell.textContent;
+          return ToolUtils.cleanText(rawValue);
+        }
+      }
+
+      const titleElements = Array.from(
+        this.table.querySelectorAll("td")
+      ).filter((td) => ToolUtils.cleanText(td.textContent) === "组织机构代码");
+
+      if (titleElements.length > 0 && titleElements[0].nextElementSibling) {
+        const valueCell = titleElements[0].nextElementSibling;
+        const rawValue =
+          valueCell.querySelector(".enter-bg-ele")?.textContent ||
+          valueCell.textContent;
+        return ToolUtils.cleanText(rawValue);
+      }
+
+      return null;
+    }
+
+    // 获取纳税人识别号
+    getTaxpayerId() {
+      const taxElements = Array.from(this.table.querySelectorAll("td")).filter(
+        (td) => ToolUtils.cleanText(td.textContent).includes("纳税人识别号")
+      );
+
+      if (taxElements.length > 0 && taxElements[0].nextElementSibling) {
+        const valueCell = taxElements[0].nextElementSibling;
+        const rawValue =
+          valueCell.querySelector(".enter-bg-ele")?.textContent ||
+          valueCell.textContent;
+        return ToolUtils.cleanText(rawValue);
+      }
+
+      const creditElements = Array.from(
+        this.table.querySelectorAll("td")
+      ).filter((td) =>
+        ToolUtils.cleanText(td.textContent).includes("统一社会信用代码")
+      );
+
+      if (creditElements.length > 0 && creditElements[0].nextElementSibling) {
+        const valueCell = creditElements[0].nextElementSibling;
+        const rawValue =
+          valueCell.querySelector(".enter-bg-ele")?.textContent ||
+          valueCell.textContent;
+        return ToolUtils.cleanText(rawValue);
+      }
+
+      return null;
+    }
+
+    // 获取参保人数
+    getInsuranceNumber() {
+      const insuranceElements = Array.from(
+        this.table.querySelectorAll("td")
+      ).filter((td) => {
+        return (
+          td.textContent.includes("参保人数") &&
+          td.querySelector(".insurance-info")
+        );
+      });
+
+      if (insuranceElements.length > 0) {
+        const valueCell = insuranceElements[0].nextElementSibling;
+        if (!valueCell) return null;
+
+        const rawText = valueCell.textContent.replace(/[\r\n\t]/g, "").trim();
+        const match = rawText.match(/(\d+人)/);
+        return match ? match[0] : null;
+      }
+
+      const registrationElements = Array.from(
+        this.table.querySelectorAll("td")
+      ).filter((td) => td.textContent.includes("登记机关"));
+
+      if (
+        registrationElements.length > 0 &&
+        registrationElements[0].previousElementSibling
+      ) {
+        const valueCell = registrationElements[0].previousElementSibling;
+        const rawText = valueCell.textContent.replace(/[\r\n\t]/g, "").trim();
+        const match = rawText.match(/(\d+人)/);
+        return match ? match[0] : null;
+      }
+
+      return null;
+    }
+
+    // 获取核准日期
+    getApprovalDate() {
+      const approvalElements = Array.from(
+        this.table.querySelectorAll(".poptip-wrap-annual-date")
+      ).filter((el) => el.textContent.includes("核准日期"));
+
+      if (approvalElements.length > 0) {
+        const valueCell = approvalElements[0].closest("td").nextElementSibling;
+        if (valueCell) {
+          const rawValue = valueCell.textContent
+            .replace(/[\r\n\t]/g, "")
+            .trim();
+          if (/^\d{4}-\d{2}-\d{2}$/.test(rawValue)) {
+            return rawValue;
+          }
+        }
+      }
+
+      const titleElements = Array.from(
+        this.table.querySelectorAll("td")
+      ).filter((td) => ToolUtils.cleanText(td.textContent) === "核准日期");
+
+      if (titleElements.length > 0 && titleElements[0].nextElementSibling) {
+        const valueCell = titleElements[0].nextElementSibling;
+        const rawValue = ToolUtils.cleanText(valueCell.textContent);
+        if (/^\d{4}-\d{2}-\d{2}$/.test(rawValue)) {
+          return rawValue;
+        }
+      }
+
+      return null;
+    }
+
+    // 解析公司信息主方法
+    parseCompanyInfo() {
+      if (!this.initTable()) return;
+
+      const companyData = {
+        企业名称: this.getOptimizedValue("企业名称"),
+        统一社会信用代码: this.getUnifiedSocialCreditCode(),
+        法定代表人: this.getLegalRepresentative(),
+        电话: this.getPhoneNumber(),
+        经营状态: this.getOptimizedValue("经营状态"),
+        成立日期: this.getOptimizedValue("成立日期"),
+        行政区划: this.getOptimizedValue("行政区划"),
+        注册资本: this.getOptimizedValue("注册资本"),
+        实缴资本: this.getOptimizedValue("实缴资本"),
+        企业类型: this.getOptimizedValue("企业类型"),
+        所属行业: this.getOptimizedValue("所属行业"),
+        工商注册号: this.getBusinessRegistrationNo(),
+        组织机构代码: this.getOrganizationCode(),
+        纳税人识别号: this.getTaxpayerId(),
+        纳税人资质: this.getOptimizedValue("纳税人资质"),
+        营业期限: this.getOptimizedValue("营业期限"),
+        核准日期: this.getApprovalDate(),
+        参保人数: this.getInsuranceNumber(),
+        登记机关: this.getOptimizedValue("登记机关"),
+        曾用名: this.getOptimizedValue("曾用名"),
+        注册地址: this.getOptimizedValue("注册地址"),
+        经营范围: this.getOptimizedValue("经营范围"),
+      };
+
+      ToolUtils.showResult(companyData);
+    }
+  }
+
+  // QCC解析类 企查查
+  class QCCParser {
+    constructor() {
+      this.table = null;
+    }
+
+    // 初始化表格
+    initTable() {
+      const cominfoNormal = document.querySelector("div.cominfo-normal");
+      if (!cominfoNormal) {
+        alert("未找到企业信息容器");
+        return false;
+      }
+
+      this.table = cominfoNormal.querySelector("table.ntable");
+      if (!this.table) {
+        alert("未找到企业信息表格");
+        return false;
+      }
+      return true;
+    }
+
+    // 获取优化后的值
+    getOptimizedValue(title) {
+      const headerCells = Array.from(this.table.querySelectorAll("td.tb"));
+      let value = null;
+
+      headerCells.forEach((header) => {
+        if (ToolUtils.cleanText(header.textContent).includes(title)) {
+          const valueCell = header.nextElementSibling;
+          if (valueCell) {
+            // 尝试从copy-value类中获取值
+            const copyValue = valueCell.querySelector(".copy-value");
+            if (copyValue) {
+              value = ToolUtils.cleanText(copyValue.textContent);
+            } else {
+              value = ToolUtils.cleanText(valueCell.textContent);
+            }
+          }
+        }
+      });
+
+      return value;
+    }
+
+    // 获取法定代表人
+    getLegalRepresentative() {
+      // Try the existing method first
+      const basicValue =
+        this.getOptimizedValue("法定代表人") || this.getOptimizedValue("法人");
+      if (basicValue && basicValue.trim()) {
+        // Remove any "关联企业 X" text
+        return basicValue.replace(/\s*关联企业\s*\d+$/, "").trim();
+      }
+
+      // If basic extraction fails, try more specific approach
+      const headerCell = Array.from(this.table.querySelectorAll("td.tb")).find(
+        (cell) => ToolUtils.cleanText(cell.textContent).includes("法定代表人")
+      );
+
+      if (!headerCell) return null;
+
+      const valueCell = headerCell.nextElementSibling;
+      if (!valueCell) return null;
+
+      // Try to find the name within the complex structure
+      // Look for anchor tags with target="_blank" which typically contain the legal representative's name
+      const nameLinks = valueCell.querySelectorAll('a[target="_blank"]');
+      for (const link of nameLinks) {
+        const name = ToolUtils.cleanText(link.textContent);
+        // Make sure it's not empty and doesn't contain obvious non-name text
+        if (name && !name.includes("关联企业") && !name.includes("复制")) {
+          return name;
+        }
+      }
+
+      // Alternative approach - look for the first anchor tag in the cell
+      const firstLink = valueCell.querySelector("a");
+      if (firstLink) {
+        const name = ToolUtils.cleanText(firstLink.textContent);
+        // Remove any trailing "关联企业 X" text
+        return name.replace(/\s*关联企业\s*\d+$/, "").trim();
+      }
+
+      // Fallback to general value extraction
+      const copyValue = valueCell.querySelector(".copy-value");
+      if (copyValue) {
+        const name = ToolUtils.cleanText(copyValue.textContent);
+        // Remove any trailing "关联企业 X" text
+        return name.replace(/\s*关联企业\s*\d+$/, "").trim();
+      }
+
+      const rawText = ToolUtils.cleanText(valueCell.textContent);
+      // Remove any trailing "关联企业 X" text
+      return rawText.replace(/\s*关联企业\s*\d+$/, "").trim();
+    }
+
+    // 获取统一社会信用代码
+    getUnifiedSocialCreditCode() {
+      return (
+        this.getOptimizedValue("统一社会信用代码") ||
+        this.getOptimizedValue("信用代码")
+      );
+    }
+
+    // 获取工商注册号
+    getBusinessRegistrationNo() {
+      return (
+        this.getOptimizedValue("工商注册号") || this.getOptimizedValue("注册号")
+      );
+    }
+
+    // 获取组织机构代码
+    getOrganizationCode() {
+      return this.getOptimizedValue("组织机构代码");
+    }
+
+    // 获取纳税人识别号
+    getTaxpayerId() {
+      return (
+        this.getOptimizedValue("纳税人识别号") ||
+        this.getUnifiedSocialCreditCode()
+      );
+    }
+
+    // 获取参保人数
+    getInsuranceNumber() {
+      // 查找参保人数表头
+      const headerCell = Array.from(this.table.querySelectorAll("td.tb")).find(
+        (cell) => ToolUtils.cleanText(cell.textContent).includes("参保人数")
+      );
+
+      if (!headerCell) return null;
+
+      const valueCell = headerCell.nextElementSibling;
+      if (!valueCell) return null;
+
+      // 提取参保人数数字
+      const numberSpan = valueCell.querySelector("span");
+      const number = numberSpan
+        ? ToolUtils.cleanText(numberSpan.textContent)
+        : null;
+
+      // 提取年报年份
+      const reportLink = valueCell.querySelector("a.m-l-r-10");
+      const reportYear = reportLink
+        ? ToolUtils.cleanText(reportLink.textContent)
+        : "";
+
+      // 组合结果
+      return number ? `${number}人 ${reportYear}` : null;
+    }
+
+    // 获取联系电话
+    getPhoneNumber() {
+      // 查找联系信息容器
+      const contactInfo = document.querySelector("div.contact-info");
+      if (!contactInfo) return null;
+
+      // 查找右侧信息区域
+      const rightPart = contactInfo.querySelector("div.main-part-item.right");
+      if (!rightPart) return null;
+
+      // 查找包含电话的行
+      const rows = Array.from(rightPart.querySelectorAll("div.rline"));
+      const phoneRow = rows.find((row) =>
+        ToolUtils.cleanText(row.textContent).includes("电话：")
+      );
+
+      if (!phoneRow) return null;
+
+      // 提取电话号码
+      const spans = Array.from(
+        phoneRow.querySelectorAll("span.need-copy-field")
+      );
+      const phoneSpan = spans.find(
+        (span) => !ToolUtils.cleanText(span.textContent).includes("电话：")
+      );
+
+      return phoneSpan ? ToolUtils.cleanText(phoneSpan.textContent) : null;
+    }
+
+    // 获取核准日期
+    getApprovalDate() {
+      return (
+        this.getOptimizedValue("核准日期") || this.getOptimizedValue("成立日期")
+      );
+    }
+
+    // 解析公司信息主方法
+    parseCompanyInfo() {
+      if (!this.initTable()) return;
+
+      const companyData = {
+        企业名称:
+          this.getOptimizedValue("企业名称") ||
+          this.getOptimizedValue("公司名称"),
+        统一社会信用代码: this.getUnifiedSocialCreditCode(),
+        法定代表人: this.getLegalRepresentative(),
+        经营状态: this.getOptimizedValue("登记状态"),
+        成立日期: this.getOptimizedValue("成立日期"),
+        行政区划: this.getOptimizedValue("行政区划"),
+        注册资本: this.getOptimizedValue("注册资本"),
+        实缴资本: this.getOptimizedValue("实缴资本"),
+        企业类型: this.getOptimizedValue("企业类型"),
+        所属行业: this.getOptimizedValue("国标行业"),
+        工商注册号: this.getBusinessRegistrationNo(),
+        组织机构代码: this.getOrganizationCode(),
+        纳税人识别号: this.getTaxpayerId(),
+        纳税人资质: this.getOptimizedValue("纳税人资质"),
+        营业期限: this.getOptimizedValue("营业期限"),
+        核准日期: this.getApprovalDate(),
+        参保人数: this.getInsuranceNumber(),
+        电话: this.getPhoneNumber(),
+        登记机关: this.getOptimizedValue("登记机关"),
+        曾用名: this.getOptimizedValue("曾用名"),
+        注册地址: this.getOptimizedValue("注册地址"),
+        经营范围: this.getOptimizedValue("经营范围"),
+      };
+
+      ToolUtils.showResult(companyData);
+    }
+  }
+
+  // 创建按钮容器
+  function createButtonContainer() {
+    const container = document.createElement("div");
+    container.id = "tool-container";
+    Object.assign(container.style, {
+      position: "fixed",
+      right: "20px",
+      bottom: "20px",
+      zIndex: "9999",
+      display: "flex",
+      flexDirection: "column",
+      gap: "10px",
+      width: "40px",
+      height: "40px",
+      backgroundColor: "#4CAF50",
+      borderRadius: "50%",
+      transition: "all 0.3s ease",
+      overflow: "hidden",
+      cursor: "move",
+    });
+
+    // +号指示器
+    const plusSign = document.createElement("div");
+    plusSign.textContent = "+";
+    Object.assign(plusSign.style, {
+      color: "white",
+      fontSize: "24px",
+      textAlign: "center",
+      lineHeight: "40px",
+      width: "100%",
+    });
+    container.appendChild(plusSign);
+
+    // 悬停展开效果
+    container.addEventListener("mouseenter", () => {
+      container.style.width = "150px";
+      container.style.height = "auto";
+      container.style.borderRadius = "8px";
+    });
+
+    container.addEventListener("mouseleave", () => {
+      container.style.width = "40px";
+      container.style.height = "40px";
+      container.style.borderRadius = "50%";
+    });
+
+    // 添加拖动功能
+    let isDragging = false;
+    let offsetX, offsetY;
+
+    // 鼠标按下开始拖动
+    container.addEventListener("mousedown", (e) => {
+      // 只有点击+号区域才允许拖动
+      if (e.target === plusSign || e.target === container) {
+        isDragging = true;
+        const rect = container.getBoundingClientRect();
+        offsetX = e.clientX - rect.left;
+        offsetY = e.clientY - rect.top;
+        container.style.cursor = "grabbing";
+        // 阻止事件冒泡和默认行为
+        e.stopPropagation();
+        e.preventDefault();
+      }
+    });
+
+    // 鼠标移动时更新位置
+    document.addEventListener("mousemove", (e) => {
+      if (!isDragging) return;
+      container.style.left = e.clientX - offsetX + "px";
+      container.style.top = e.clientY - offsetY + "px";
+      container.style.right = "auto";
+      container.style.bottom = "auto";
+    });
+
+    // 鼠标释放结束拖动
+    document.addEventListener("mouseup", () => {
+      if (isDragging) {
+        isDragging = false;
+        container.style.cursor = "move";
+      }
+    });
+    // 创建功能按钮
+    function createButton(text, onClick) {
+      const button = document.createElement("button");
+      button.textContent = text;
+      Object.assign(button.style, {
+        padding: "8px 12px",
+        border: "none",
+        borderRadius: "4px",
+        backgroundColor: "white",
+        color: "#333",
+        cursor: "pointer",
+        width: "100%",
+        transition: "backgroundColor 0.2s",
+      });
+      button.addEventListener(
+        "mouseenter",
+        () => (button.style.backgroundColor = "#f0f0f0")
+      );
+      button.addEventListener(
+        "mouseleave",
+        () => (button.style.backgroundColor = "white")
+      );
+      button.addEventListener("click", onClick);
+      return button;
+    }
+
+    // 复制源码按钮
+    const copySourceButton = createButton("复制源码", () => {
+      const html = document.documentElement.outerHTML;
+
+      copyToClipboard(html, "HTML源码已复制到剪贴板");
+      /*
+      navigator.clipboard
+        .writeText(html)
+        .then(() => {
+          alert("源码已复制到剪贴板");
+        })
+        .catch((err) => {
+          console.error("复制失败:", err);
+        });
+        */
+    });
+
+    // 解析公司信息按钮
+    const parseInfoButton = createButton("解析公司信息", () => {
+      // 根据当前URL选择对应的解析器
+      let parser;
+      if (window.location.host.includes("aiqicha.baidu.com")) {
+        parser = new AiQiChaParser();
+      } else if (window.location.host.includes("qcc.com")) {
+        parser = new QCCParser();
+      } else {
+        alert("不支持的网站");
+        return;
+      }
+      parser.parseCompanyInfo();
+    });
+
+    // 添加按钮到容器
+    container.appendChild(copySourceButton);
+    container.appendChild(parseInfoButton);
+
+    document.body.appendChild(container);
+  }
+
+  // 页面加载完成后创建按钮
+  window.addEventListener("load", createButtonContainer);
+})();

config.py

@@ -0,0 +1,23 @@
+
+
+# 最好写入三家搜索引擎登录后的cookie
+bingheaders = {
+    'cookie': """""",
+    'referer': 'https://cn.bing.com/',
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/82.0.4051.0 Safari/537.36 Edg/82.0.425.0'}
+
+baiduheaders = {
+    'Cookie': """PSTM=1755051967; BAIDUID=9623ABA6AF15935E519C6D57EB04D5BD:FG=1; BIDUPSID=BFDEAE9917763352A1CF94FF7A9AD50F; BD_UPN=12314753; delPer=0; BD_CK_SAM=1; PSINO=3; BAIDUID_BFESS=9623ABA6AF15935E519C6D57EB04D5BD:FG=1; ZFY=LX6tLiXJLyE8Spg0Tn3yWYhYWOqUXgNuD45NXzSsgDY:C; baikeVisitId=6e4f6130-a8eb-49b3-8413-1815a6af31a3; BD_HOME=1; ppfuid=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; BDUSS=o4ZFV6UTVucGp0Rmx6TlNucFQ1Z1FEMnQyZ1ZOdmRUZWg2Nn5FQWxteWdBTVZvSVFBQUFBJCQAAAAAAAAAAAEAAAAXn3lCu8PRqdTGtssAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAKBznWigc51oZW; BDUSS_BFESS=o4ZFV6UTVucGp0Rmx6TlNucFQ1Z1FEMnQyZ1ZOdmRUZWg2Nn5FQWxteWdBTVZvSVFBQUFBJCQAAAAAAAAAAAEAAAAXn3lCu8PRqdTGtssAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAKBznWigc51oZW; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%22370464293%22%2C%22first_id%22%3A%22198a7105b40582-0a1b1b0944bf378-4c657b58-1440000-198a7105b4183a%22%2C%22props%22%3A%7B%7D%2C%22%24device_id%22%3A%22198a7105b40582-0a1b1b0944bf378-4c657b58-1440000-198a7105b4183a%22%7D; MCITY=-179%3A; log_first_time=1755482524636; log_last_time=1755482544322; RT="z=1&dm=baidu.com&si=1403e7da-9af8-439d-bdca-61f492a1b52a&ss=mecm9ry0&sl=0&tt=0&bcn=https%3A%2F%2Ffclog.baidu.com%2Flog%2Fweirwood%3Ftype%3Dperf&ld=jhi&ul=3upx87&hd=3upxa3"; H_PS_PSSID=62325_63147_63327_63948_64048_64174_64248_64245_64258_64260_64317_64358_64366_64362_64363_64395_64414_64429_64436_64442_64450_64457_64473_64483_64502_64512_64448_64087_64559_64571; BA_HECTOR=048lak8h81218h8h8020850k80a00g1ka54mp25; H_WISE_SIDS=62325_63147_63327_63948_64048_64174_64248_64245_64258_64260_64317_64358_64366_64362_64363_64395_64414_64429_64436_64442_64450_64457_64473_64483_64502_64512_64448_64087_64559_64571; BDRCVFR[feWj1Vr5u3D]=I67x6TjHwwYf0; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; COOKIE_SESSION=21_0_8_9_13_23_0_1_8_9_1_6_498875_0_0_0_1754446941_0_1755485313%7C9%231543375_16_1753882701%7C7; H_PS_645EC=1275d4%2BgYNOGPU5%2Fgp6XcloUiDEOGWs8LNx7nISyDCmJSXMYxQLNnwJypIA""",
+    'Host': 'www.baidu.com',
+    'referer': 'https://www.baidu.com/s',
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/139.0.0.0 Safari/537.36 Edg/139.0.0.0'
+}
+googleheaders = {
+    'cookie': """""",
+    'referer': 'https://www.google.com/',
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36'
+}
+
+# 爬取谷歌需要代理
+proxy='http://127.0.0.1:7897'
+

data.csv

@@ -0,0 +1,69 @@
+杭州辉煌物业管理有限公司
+杭州辉望科技有限公司
+浙江八方电信科技集团有限公司
+中国移动通信集团浙江有限公司余杭分公司西溪八方城（自营厅）
+瑞凤九天（杭州）科技有限公司
+金码智能科技（杭州）有限公司
+OPPO广东移动通信有限公司
+杭州巨量引擎网络技术有限公司
+杭州绿城衡宇环境设计有限公司
+新疆浙疆果业有限公司
+杭州未知数品牌管理有限公司
+杭州慈山科技有限公司
+杭州扬拓体育科技有限公司
+杭州乂游网络科技有限公司
+杭州钱橙似锦科技有限公司
+杭州奥得徕贸易有限公司
+杭州伍壹荟旅游咨资询有限公司
+杭州心满意定供应链服务有限公司
+杭州麒晨科技有限公司
+杭州羊咩咩文化传媒有限公司
+杭州禾露则正生物科技有限公司
+浙江商盟支付有限公司
+天禄（杭州）科技有限公司
+如是启创（杭州）科技有限公司
+杭州音视贝科技有限公司
+杭州千骏轴承有限公司
+杭州锐擎科技有限公司
+浙江力一科技有限公司
+煜邦电力智能装备(嘉兴)有限公司
+杭州裕阳经营管理合伙企业(有限合伙)
+氧气.康复中心
+杭州云迹物联科技有限公司
+杭州着墨文化创意者限公司
+亚信科技（南京）有限公司
+杭州密尔沃智能装备有限公司
+杭州骏远电子商务有限公司
+杭州一喂智能科技有限公司
+杭州孚伦特科技有限公司
+杭州人谋天成科技有限公司
+杭州瑾馨贸易集团有限公司
+杭州琑为缘文化艺术有限公司
+浙江丝里伯睡眠科技股份有限公司
+杭州倍驰科技有限公司
+杭州心灵部落教育有限公司（灵动生活）
+杭州云印智造科技有限公司
+浙江海拓环境技术有限公司
+申能环境科技有限公司
+医贝云服（杭州）科技有限公司
+杭州甬盛通信技术有限公司
+杭州字节跳动科技有限公司
+杭州邻汇网络科技有限公司
+浙江建盛安全科技有限公司
+幻想集团·杭州运营中心
+杭州阿克莱斯设备有限公司
+浙江省现代农业促进会
+益思芯科技（杭州）有限公司
+杭州霖思网络科技有限公司
+杭州星瀚知识产权代理有限公司
+风华（杭州）信息技术有限公司
+杭州晓羽科技有限公司
+浙江根旺律师事务所
+远大住宅工业（杭州）有限公司
+浙江全应科技有限公司
+杭州塞牧文化传媒有限公司
+浙江彩屋信息技术有限公司
+杭州瑞泡特教育科技有限公司
+杭州贝享健康科技有限公司
+杭州摸象大数据科技有限公司
+杭州颐刻生物科技有限公司

freeze.bat

@@ -0,0 +1 @@
+pip freeze > requirements.txt

install_requirements.bat

@@ -0,0 +1,2 @@
+pip install -r requirements.txt
+python.exe -m pip install --upgrade pip

main.py

@@ -0,0 +1,138 @@
+# -*- coding: utf-8 -*-
+import asyncio
+import random
+
+import aiohttp
+import time
+import sys
+from bs4 import BeautifulSoup
+import re
+import aiofiles
+import urllib.parse
+import argparse
+from colorama import init, Fore
+from search import Bing,Baidu
+import openpyxl
+import ssl
+
+from tool.read_csv import CSVReader
+
+start = time.time()
+def printascii():
+    # 初始化
+    init()
+    # 设置颜色
+    print(Fore.GREEN + r'''
+  ____                      _               
+ / ___|  ___  __ _ _ __ ___| |__   ___ _ __ 
+ \___ \ / _ \/ _` | '__/ __| '_ \ / _ \ '__|
+  ___) |  __/ (_| | | | (__| | | |  __/ |   
+ |____/ \___|\__,_|_|  \___|_| |_|\___|_|   
+''' + Fore.RESET)
+# 天欣安全实验室
+
+
+def writeExcel(titles, links,ws):
+    infos = list(zip(titles, links))
+    for row in infos:
+        ws.append(row)
+
+def create_sheet_and_write(wb, engine, keywords, num, title):
+    ws = wb.create_sheet(title=title)
+    result = engine(keywords, num)
+    writeExcel(result[0], result[1], ws)
+def excel_text2url(link_url): #如果函数内部没有进行异步操作，使用 async 并不会对性能或功能产生实际影响。
+    '''把一个网址字符串转换为 Excel公式，使其可以点击直接转跳'''
+    return f'=HYPERLINK("{link_url}","{link_url}")'
+# 遍历所有工作表，并将第二列的所有数据传递给 excel_text2url 函数重新赋值
+def update_hyperlinks(wb):
+    for sheet in wb.worksheets:  # 遍历每一个工作表
+        for row in sheet.iter_rows(min_row=1, max_row=sheet.max_row, min_col=2, max_col=2):  # 遍历第二列
+            for cell in row:
+                if cell.value:  # 检查单元格是否有内容
+                    cell.value = excel_text2url(cell.value)  # 将网址转换为超链接公式
+                else:
+                    break
+
+def commend():
+    parser = argparse.ArgumentParser(prog="Searcher", description='此工具用于对百度、必应和谷歌搜索的协程爬取--天欣安全实验室', usage='please read -h')
+    parser.add_argument("-k", type=str, help="搜索的关键词", nargs='+')
+    # 添加一个positional arguments，叫a,读取类型为int（默认是字符串）
+    parser.add_argument("-p", type=str, help="需要搜索页数,默认为5,支持范围搜索，例如搜索从第2页到第五页的参数为 2:5", default='5')
+    parser.add_argument("-m", type=str, help="使用的搜索引擎:百度:bd,必应:bin,谷歌:goo 不填写默认使用全部", default='all',nargs='+')
+    # parser.add_argument("-t", '--task', type=int, help="设置的线程,默认为8", default=8)
+    parser.exit_on_error = False
+    args = parser.parse_args()
+    if len(sys.argv) == 1:
+        printascii()
+        parser.print_help()
+        sys.exit()
+    return args
+def search_company_info(company_name_arg, num):
+    keywords = company_name_arg
+    # for key in keyword:
+    #     keywords = keywords + key + " "
+    keywords = keywords.strip()
+    result = Bing.bing_main(keywords, num)
+
+    # for 循环 遍历 result[0] 和 result[1]
+
+    data_list =[]
+    for i in range(len(result[0])):
+        title= result[0][i]
+        url = result[1][i]
+        print(f"必应搜索爬取结果为,title:{title}, url:{url}")
+        if re.match(r"^https://aiqicha.baidu.com/company_detail_.*|https://www.qcc.com/firm/.*|https://www.tianyancha.com/company/.*", url):
+           data_list.append([title, url])
+    return data_list
+
+def filter_company_sites(urls):
+    # urls https://www.tianyancha.com/company/5226478758
+    # url:https://aiqicha.baidu.com/company_detail_26602790857925
+    # url:https://www.qcc.com/firm/05b449eb5cc417d0f97c14104051f5c0.html
+    # 匹配 前缀https://aiqicha.baidu.com/company_detail_*,https://www.qcc.com/firm/*.html,https://www.tianyancha.com/company/5226478758*
+    filtered_urls = [url for url in urls if re.match(r"^https://aiqicha.baidu.com/company_detail_.*|https://www.qcc.com/firm/.*|https://www.tianyancha.com/company/.*", url)]
+    return filtered_urls
+
+
+def search_one_company(company_name_arg, num):
+
+    keywords = company_name_arg
+    # for key in keyword:
+    #     keywords = keywords + key + " "
+    keywords = keywords.strip()
+    print(f"您搜索的关键词为:{keywords}")
+    wb = openpyxl.Workbook()
+    # 删除默认创建的工作表（现在名为 "数据表1"）
+    wb.remove(wb['Sheet'])
+    printascii()
+    pattern = r"[\\/:\*\?\"<>|]"
+    keyword = re.sub(pattern, "", keywords)
+    create_sheet_and_write(wb, Bing.bing_main, keywords, num, "必应爬取结果")
+    create_sheet_and_write(wb, Baidu.baidu_main, keywords, num, "百度爬取结果")
+    # 将所有url变为超链接,点击即可打开转跳
+    update_hyperlinks(wb)
+    wb.save(f'./{keyword}-{company_name_arg}.xlsx')
+    print(Fore.GREEN + '总任务结束!' + Fore.RESET)
+    end = time.time()
+    print(Fore.RED + f'脚本总时间: {end - start:.2f}')
+
+if __name__ == '__main__':
+    reader = CSVReader('data.csv')
+    company_names = reader.read_column(0, has_header=False)
+    print("所有数据:", company_names)
+
+    i= 1
+    for company_name in company_names:
+        sleep_time = 5
+        sleep_time += random.randint(1, 5)
+        time.sleep(sleep_time)
+        company_name += " 爱企查|企查查"
+        data_list = search_company_info(company_name, '1')
+        print(data_list)
+        i=i+1
+        if i > 1:
+            break
+
+
+

requirements.txt

@@ -0,0 +1,20 @@
+aiofiles==24.1.0
+aiohappyeyeballs==2.4.0
+aiohttp==3.10.5
+aiosignal==1.3.1
+async-timeout==4.0.3
+attrs==24.2.0
+beautifulsoup4==4.12.3
+colorama==0.4.6
+et-xmlfile==1.1.0
+frozenlist==1.4.1
+greenlet==3.2.4
+idna==3.8
+lxml==5.3.0
+multidict==6.1.0
+openpyxl==3.1.5
+playwright==1.55.0
+pyee==13.0.0
+soupsieve==2.6
+typing_extensions==4.12.2
+yarl==1.11.1

search/Baidu.py

@@ -0,0 +1,128 @@
+# -*- coding: utf-8 -*-
+import os
+import asyncio
+import aiohttp
+import time
+import sys
+from bs4 import BeautifulSoup
+import re
+import aiofiles
+import urllib.parse
+import argparse
+from colorama import init, Fore
+import ssl
+from urllib.parse import quote
+# 添加项目根目录到 sys.path
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+import config
+baiduheaders=config.baiduheaders
+
+timeout = aiohttp.ClientTimeout(
+    total=None,  # 总超时
+    sock_connect=5.5,  # 连接超时时间5.5
+    sock_read=5.5  # 读取超时为5.5秒
+)
+#--天欣安全实验室--#
+
+# 初次请求获取百度加密后的url
+async def getfirstinfo(keyword, pn,session):
+    sslcontext = ssl.create_default_context()
+    sslcontext.check_hostname = False
+    sslcontext.verify_mode = ssl.CERT_NONE
+    titlelist = []
+    fakeurl = []
+    url = f'https://www.baidu.com/s?wd={keyword}&pn={pn}'
+    # print("正在爬取的url为:"+url)
+    j=0
+    while j<3:
+        try:
+            async with session.get(url, headers=baiduheaders, ssl=sslcontext,timeout=timeout) as resp:
+                html = await resp.text()
+                soup = BeautifulSoup(html, 'lxml')
+                h3 = soup.select('h3.t')
+                for h3 in h3:
+                    h3text = h3.text.replace('\n', '').replace(',', ' ').replace('\ue636', '').strip()
+                    titlelist.append(h3text) #保存h3标签内的文字内容
+                    fakeurl.append(h3.a.get('href')) #获取h3下a标签的href链接，此链接为百度跳转链接，需要处理
+            return titlelist, fakeurl
+        except Exception as e:
+            # print(e)
+            print("baidu链接失败，正在重新尝试...")
+        j=j+1
+    print(f"百度任务出错:{url}该url无法正常获取数据。")
+    return [],[]
+
+# 再次请求获取真实的网站url
+async def gettrueurl(url,printtitle,session):
+    try:
+        domain = 'https://www.baidu.com/'
+        # async with aiohttp.ClientSession() as session:
+        async with session.get(url, headers=baiduheaders, allow_redirects=False) as resp:
+            await resp.text()
+            if str(resp.headers.get('Location')) != None and str(resp.headers.get('Location')) != '':
+                trueurl=str(resp.headers.get('Location'))
+                print(printtitle," ",trueurl)
+                return trueurl
+            else:
+                print(url + '该url无法转跳')
+                url = urllib.parse.urljoin(domain, url)
+                print(printtitle, " ",url)
+                return url
+    except:
+        return url
+
+
+
+
+async def baidu_spinder(keyword, num):
+    print(f'百度爬取任务进行中,爬取页数为{num}...')
+    urllist = []
+    titlelist = []
+    tasks1 = []
+    tasks2 = []
+    Source = []
+    if ':' in num:
+        if num.count(':') > 1:
+            raise ValueError("输入中必须且只能包含一个 ':'")
+        else:
+            # 分割字符串，确保分割后的两部分都是数字
+            start_page, end_page = num.split(':')
+            # 判断两边是否都是数字
+            if not (start_page.isdigit() and end_page.isdigit()):
+                raise ValueError("':' 两侧的值必须是数字")
+            else:
+                start_page = (int(start_page) - 1) * 10
+                end_page = (int(end_page)) * 10
+    else:
+        start_page, end_page = 0, int(num) * 10
+    async with aiohttp.ClientSession() as session:
+        for i, pn in enumerate(range(start_page, end_page, 10)):
+            tasks1 = tasks1 + [asyncio.create_task(getfirstinfo(keyword, pn,session))]
+        result = await asyncio.gather(*tasks1)
+    async with aiohttp.ClientSession() as session:
+        for i in range(int((end_page-start_page) / 10)):
+            titlelist += result[i][0]
+            for j,url in enumerate(result[i][1]):
+                printtitle=result[i][0][j]
+                if not url.startswith(('http://', 'https://')):
+                    domain = 'http://www.baidu.com/'
+                    url = urllib.parse.urljoin(domain, url)
+                tasks2 = tasks2 + [asyncio.create_task(gettrueurl(url,printtitle,session))]
+        print('标题\t                                     URL\t')
+        urllist += await asyncio.gather(*tasks2)
+    count = len(urllist)
+    print(f"百度搜索爬取结果数量为{count}")
+    print(Fore.GREEN + '百度爬取任务完成！\n' + Fore.RESET)
+    return titlelist, urllist
+    # await baiduwriteCSV(titlelist, urllist, keyword)
+
+
+def baidu_main(keyword, num):
+    keyword = quote(keyword)
+    if sys.platform.startswith('win'):
+        asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())
+    loop = asyncio.get_event_loop()
+    return loop.run_until_complete(baidu_spinder(keyword, num))
+
+async def Baidu_main(keywords, num):
+    return await baidu_spinder(keywords, num)

search/Bing.py

@@ -0,0 +1,90 @@
+# -*- coding: utf-8 -*-
+import asyncio
+import os
+import sys
+import urllib.parse
+from urllib.parse import quote
+import aiohttp
+from bs4 import BeautifulSoup
+from colorama import Fore
+
+# 添加项目根目录到 sys.path
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+import config
+bingheaders=config.bingheaders
+proxy=config.proxy
+timeout = aiohttp.ClientTimeout(
+    total=None,  # 总超时
+    sock_connect=5.5,  # 连接超时时间5.5
+    sock_read=5.5  # 读取超时为5.5秒
+)
+async def getbing(url, session):
+    url_list = []
+    title_list = []
+    async with session.get(url, headers=bingheaders,timeout=timeout) as resp:
+        # print("正在爬取url:"+url)
+        try:
+            a = await resp.text()
+            soup = BeautifulSoup(a, 'lxml')
+            h2a = soup.select('h2 a')
+            for h in h2a:
+                htext = h.text.replace('\n', '').replace(',', ' ').strip()
+                hurl=h.get('href')
+                if not hurl.startswith(('http://', 'https://')):
+                    domain = 'https://cn.bing.com/'
+                    hurl = urllib.parse.urljoin(domain, hurl)
+                print(htext,"  ",hurl)
+                title_list.append(htext)
+                url_list.append(hurl)
+        except:
+            print(f"必应页面爬取失败,{url}该url无法正常获取数据。")
+            return [],[]
+    return url_list, title_list
+
+
+async def bing_spinder(keyword, num):
+    print(f'必应爬取任务进行中,爬取页数为{num}...')
+    print('标题                  url')
+    urllist = []
+    titlelist = []
+    tasks = []
+    if ':' in num:
+        if num.count(':') > 1:
+            raise ValueError("输入中必须且只能包含一个 ':'")
+        else:
+            # 分割字符串，确保分割后的两部分都是数字
+            start_page, end_page = num.split(':')
+            # 判断两边是否都是数字
+            if not (start_page.isdigit() and end_page.isdigit()):
+                raise ValueError("':' 两侧的值必须是数字")
+            else:
+                start_page = (int(start_page)-1)*10
+                end_page = (int(end_page))*10
+    else:
+        start_page, end_page =0,int(num) * 10
+    async with aiohttp.ClientSession() as session:
+        for pn in range(start_page, end_page, 10):
+            #url = f'https://cn.bing.com/search?q={keyword}&first={pn}&mkt=zh-CN'
+            url = f'https://cn.bing.com/search?q={keyword}&qs=n&form=QBRE&sp=-1&lq=0'
+            # print("正在爬取的url为:"+url)
+            tasks = tasks + [asyncio.create_task(getbing(url, session))]
+        result = await asyncio.gather(*tasks)
+    for i in range(int((end_page-start_page) / 10)):
+        urllist += result[i][0]
+        titlelist += result[i][1]
+    count=len(urllist)
+    print(f"必应搜索爬取结果为{count}")
+    print(Fore.GREEN + '必应爬取任务完成\n' + Fore.RESET)
+    return titlelist, urllist
+    # await bingwriteCSV(titlelist, urllist, keyword)
+
+
+def bing_main(keyword,num):
+    keyword = quote(keyword)
+    if sys.platform.startswith('win'):
+        asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())
+    loop = asyncio.get_event_loop()
+    return loop.run_until_complete(bing_spinder(keyword,num))
+
+async def Bing_main(keywords, num):
+    return await bing_spinder(keywords, num)

tool/read_csv.py

@@ -0,0 +1,190 @@
+import csv
+from typing import List, Dict, Union, Any, Optional
+
+class CSVReader:
+    """
+    CSV文件读取工具类
+    支持有表头和无表头模式，可按列索引或表头字段名返回数据
+    """
+
+    def __init__(self, file_path: str):
+        """
+        初始化CSV读取器
+
+        Args:
+            file_path: CSV文件路径
+        """
+        self.file_path = file_path
+
+    def read(self, has_header: bool = True, encoding: str = 'utf-8') -> List[Dict[str, Any]]:
+        """
+        读取CSV文件并返回查询结果
+
+        Args:
+            has_header: 是否有表头，默认为True
+            encoding: 文件编码，默认为utf-8
+
+        Returns:
+            List[Dict[str, Any]]: 查询结果列表，每个元素是一行数据的字典表示
+        """
+        data = []
+
+        with open(self.file_path, 'r', encoding=encoding) as file:
+            if has_header:
+                # 使用DictReader处理有表头的CSV
+                reader = csv.DictReader(file)
+                for row in reader:
+                    data.append(dict(row))
+            else:
+                # 使用普通reader处理无表头的CSV
+                reader = csv.reader(file)
+                for row in reader:
+                    # 为无表头的行创建字典，使用列索引作为键
+                    row_dict = {f'col_{i}': value for i, value in enumerate(row)}
+                    data.append(row_dict)
+
+        return data
+
+    def read_column(self, column: Union[int, str], has_header: bool = True,
+                   encoding: str = 'utf-8') -> List[Any]:
+        """
+        读取指定列的数据
+
+        Args:
+            column: 列索引(从0开始)或列名
+            has_header: 是否有表头
+            encoding: 文件编码
+
+        Returns:
+            List[Any]: 指定列的数据列表
+        """
+        data = self.read(has_header, encoding)
+
+        if has_header and isinstance(column, str):
+            # 有表头且指定了列名
+            return [row[column] for row in data]
+        elif isinstance(column, int):
+            # 指定了列索引
+            if has_header:
+                # 有表头时需要获取列名
+                if data:
+                    keys = list(data[0].keys())
+                    if 0 <= column < len(keys):
+                        column_name = keys[column]
+                        return [row[column_name] for row in data]
+                    else:
+                        raise IndexError(f"Column index {column} out of range")
+                else:
+                    return []
+            else:
+                # 无表头时使用默认列名
+                column_name = f'col_{column}'
+                return [row[column_name] for row in data if column_name in row]
+        else:
+            raise ValueError("Invalid column parameter")
+
+    def read_columns(self, columns: Dict[str, Union[int, str]], has_header: bool = True,
+                    encoding: str = 'utf-8') -> List[Dict[str, Any]]:
+        """
+        读取指定的多列数据，可以重命名列名
+
+        Args:
+            columns: 字典，键为返回结果中的列名，值为原CSV中的列索引或列名
+            has_header: 是否有表头
+            encoding: 文件编码
+
+        Returns:
+            List[Dict[str, Any]]: 指定列的数据列表
+        """
+        all_data = self.read(has_header, encoding)
+        result = []
+
+        # 获取所有列名
+        if all_data:
+            header_keys = list(all_data[0].keys())
+        else:
+            header_keys = []
+
+        for row in all_data:
+            new_row = {}
+            for new_name, old_column in columns.items():
+                if isinstance(old_column, str) and has_header:
+                    # 按列名获取值
+                    new_row[new_name] = row.get(old_column, '')
+                elif isinstance(old_column, int):
+                    # 按列索引获取值
+                    if has_header:
+                        if 0 <= old_column < len(header_keys):
+                            key = header_keys[old_column]
+                            new_row[new_name] = row.get(key, '')
+                        else:
+                            new_row[new_name] = ''
+                    else:
+                        key = f'col_{old_column}'
+                        new_row[new_name] = row.get(key, '')
+            result.append(new_row)
+
+        return result
+
+# 使用示例
+if __name__ == "__main__":
+    # 示例1: 有表头的CSV文件
+    # 假设有一个名为data.csv的文件内容如下:
+    # name,age,city
+    # Alice,25,Beijing
+    # Bob,30,Shanghai
+    # Charlie,35,Guangzhou
+
+    reader = CSVReader('../data.csv')
+    # 读取所有数据
+    #all_data = reader.read(has_header=False)
+    # 读取所有数据
+    # all_data = reader.read(has_header=True)
+
+
+    # print("所有数据:", all_data)
+
+    selected_data_no_header = reader.read_columns({
+        'company_name': 0
+    }, has_header=False)
+    print("所有数据:", selected_data_no_header)
+
+    selected_data_no_header = reader.read_column(0, has_header=False)
+    print("所有数据:", selected_data_no_header)
+    # # 读取指定列(按列名)
+    # names = reader.read_column('name', has_header=True)
+    # print("姓名列:", names)
+    #
+    # # 读取指定列(按索引)
+    # ages = reader.read_column(1, has_header=True)
+    # print("年龄列:", ages)
+    #
+    # # 读取多列并重命名
+    # selected_data = reader.read_columns({
+    #     '姓名': 'name',
+    #     '年龄': 1
+    # }, has_header=True)
+    # print("选择的数据:", selected_data)
+    #
+    # # 示例2: 无表头的CSV文件
+    # # 假设有一个名为data_no_header.csv的文件内容如下:
+    # # Alice,25,Beijing
+    # # Bob,30,Shanghai
+    # # Charlie,35,Guangzhou
+    #
+    # reader2 = CSVReader('data_no_header.csv')
+    #
+    # # 读取所有数据
+    # all_data_no_header = reader2.read(has_header=False)
+    # print("无表头所有数据:", all_data_no_header)
+    #
+    # # 读取指定列(按索引)
+    # first_column = reader2.read_column(0, has_header=False)
+    # print("第一列:", first_column)
+    #
+    # # 读取多列并指定名称
+    # selected_data_no_header = reader2.read_columns({
+    #     '姓名': 0,
+    #     '城市': 2
+    # }, has_header=False)
+    # print("无表头选择的数据:", selected_data_no_header)