From 00603f5311d4f1d8b743be1f2f3a2e989c874556 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=A2=A6=E6=83=B3=E6=A9=A1=E7=9A=AE=E6=93=A6?=
 <seozzz@163.com>
Date: Tue, 31 Aug 2021 15:13:38 +0800
Subject: [PATCH] =?UTF-8?q?=E9=9D=9E=E9=81=97=E6=95=B0=E6=8D=AE?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 ...36\351\201\227\346\225\260\346\215\256.py" | 50 +++++++++++++++++++
 ...7\344\273\266\347\233\256\345\275\225.txt" |  0
 2 files changed, 50 insertions(+)
 create mode 100644 "NO25/\351\235\236\351\201\227\346\225\260\346\215\256.py"
 create mode 100644 "NO25/\351\235\236\351\201\227\346\225\260\346\215\256/\346\226\207\344\273\266\347\233\256\345\275\225.txt"

diff --git "a/NO25/\351\235\236\351\201\227\346\225\260\346\215\256.py" "b/NO25/\351\235\236\351\201\227\346\225\260\346\215\256.py"
new file mode 100644
index 0000000..ca3d325
--- /dev/null
+++ "b/NO25/\351\235\236\351\201\227\346\225\260\346\215\256.py"
@@ -0,0 +1,50 @@
+import threading
+import requests
+import random
+
+class Common:
+    def __init__(self):
+        pass
+
+    def get_headers(self):
+        uas = [
+            "Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)",
+            "你自己的UA值，或者可以从之前的博客中获取"
+        ]
+        ua = random.choice(uas)
+        headers = {
+            "user-agent": ua,
+            "referer": "https://www.baidu.com"
+        }
+        return headers
+
+
+def run(index, url, semaphore, headers):
+    semaphore.acquire()  # 加锁
+    res = requests.get(url, headers=headers, timeout=5)
+    res.encoding = 'utf-8'
+    text = res.text
+    save(index,text)
+    semaphore.release()  # 释放
+
+# 存储的数据中文进行了 UNICODE 编码，分析的时候注意转化
+def save(index, text):
+    with open(f"./非遗数据/{index}.json", "w", encoding="utf-8") as f:
+        f.write(f"{text}")
+    print("该URL地址数据写入完毕")
+
+
+if __name__ == '__main__':
+    c = Common()
+    url_format = 'http://www.ihchina.cn/Article/Index/getProject.html?province=&rx_time=&type=&cate=&keywords=&category_id=16&limit=10&p={}'
+    # 拼接URL，全局共享变量，362 页直接设置，没有动态获取
+    urls = [url_format.format(i) for i in range(1, 362)]
+    # 最多允许5个线程同时运行
+    semaphore = threading.BoundedSemaphore(5)
+    for i, url in enumerate(urls):
+        t = threading.Thread(target=run, args=(i, url, semaphore, c.get_headers()))
+        t.start()
+    while threading.active_count() != 1:
+        pass
+    else:
+        print('所有线程运行完毕')
diff --git "a/NO25/\351\235\236\351\201\227\346\225\260\346\215\256/\346\226\207\344\273\266\347\233\256\345\275\225.txt" "b/NO25/\351\235\236\351\201\227\346\225\260\346\215\256/\346\226\207\344\273\266\347\233\256\345\275\225.txt"
new file mode 100644
index 0000000..e69de29
-- 
GitLab