aiqicha

company/qcc_crawler.py

@@ -0,0 +1,86 @@
+from playwright.sync_api import sync_playwright
+import json
+import os
+import time
+
+COOKIE_FILE = "qcc_cookies.json"
+
+
+def ensure_cookie_file():
+    if not os.path.exists(COOKIE_FILE):
+        with open(COOKIE_FILE, 'w') as f:
+            json.dump([], f)
+        print(f"已创建新的cookie文件: {COOKIE_FILE}")
+
+
+def save_cookies(context):
+    cookies = context.cookies()
+    with open(COOKIE_FILE, 'w') as f:
+        json.dump(cookies, f, indent=2)
+    print(f"Cookies已保存到 {COOKIE_FILE}")
+
+
+def load_cookies(context):
+    try:
+        with open(COOKIE_FILE, 'r') as f:
+            cookies = json.load(f)
+            if cookies:
+                context.add_cookies(cookies)
+                return True
+        return False
+    except Exception as e:
+        print(f"加载cookies失败: {str(e)}")
+        return False
+
+
+def qcc_login(page):
+    page.goto("https://www.qcc.com")
+    page.wait_for_selector(".login-container", timeout=5000)
+    page.click("text=扫码登录")
+
+    print("请扫描页面二维码登录...")
+    page.wait_for_url("**/usercenter**", timeout=120000)
+    print("登录成功！")
+
+
+def search_company(page, company_name):
+    page.goto(f"https://www.qcc.com/web/search?key={company_name}")
+    page.wait_for_selector(".search-result-item", timeout=10000)
+
+    # 示例数据提取
+    company_info = {
+        "name": page.locator(".company-name").first.inner_text(),
+        "legal_rep": page.locator(".legal-person").first.inner_text(),
+        "status": page.locator(".company-status").first.inner_text()
+    }
+    return company_info
+
+
+def main():
+    ensure_cookie_file()
+
+    with sync_playwright() as p:
+        browser = p.chromium.launch(headless=False)
+        context = browser.new_context()
+        page = context.new_page()
+
+        if not load_cookies(context):
+            qcc_login(page)
+            save_cookies(context)
+
+        companies = ["阿里巴巴", "腾讯科技", "华为技术"]
+        for company in companies:
+            try:
+                info = search_company(page, company)
+                print(f"{info['name']} | 法人:{info['legal_rep']} | 状态:{info['status']}")
+                save_cookies(context)  # 每次操作后更新cookies
+                time.sleep(3)
+            except Exception as e:
+                print(f"查询 {company} 失败: {str(e)}")
+
+        context.close()
+        browser.close()
+
+
+if __name__ == "__main__":
+    main()