From 737404a1babee8d80641753c908c031c4b0e1592 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 15:01:34 +0800
Subject: [PATCH] =?UTF-8?q?=E8=99=8E=E7=89=99=E7=9B=B4=E6=92=AD=E6=95=B0?=
 =?UTF-8?q?=E6=8D=AE=E9=87=87=E9=9B=86?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 "NO24/\350\231\216\347\211\231.py"            | 62 +++++++++++++++++++
 .../\347\251\272\347\233\256\345\275\225.txt" |  0
 2 files changed, 62 insertions(+)
 create mode 100644 "NO24/\350\231\216\347\211\231.py"
 create mode 100644 "NO24/\350\231\216\347\211\231/\347\251\272\347\233\256\345\275\225.txt"

diff --git "a/NO24/\350\231\216\347\211\231.py" "b/NO24/\350\231\216\347\211\231.py"
new file mode 100644
index 0000000..33e003a
--- /dev/null
+++ "b/NO24/\350\231\216\347\211\231.py"
@@ -0,0 +1,62 @@
+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)",
+            "其余内容"
+        ]
+        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
+    text = text.replace('getLiveListJsonpCallback(', '')
+    text = text[:-1]
+    # print(text)
+    # json_data = json.loads(text)
+    # print(json_data)
+    save(index,text)
+    semaphore.release()  # 释放
+
+
+def save(index, text):
+    with open(f"./虎牙/{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__':
+    # 获取总页码
+    first_url = 'https://www.huya.com/cache.php?m=LiveList&do=getLiveListByPage&tagAll=0&callback=&page=1'
+    c = Common()
+    res = requests.get(url=first_url, headers=c.get_headers())
+    data = res.json()
+    if data['status'] == 200:
+        total_page = data['data']['totalPage']
+
+    url_format = 'https://www.huya.com/cache.php?m=LiveList&do=getLiveListByPage&tagAll=0&callback=&page={}'
+    # 拼接URL，全局共享变量
+    urls = [url_format.format(i) for i in range(1, total_page)]
+    # 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/NO24/\350\231\216\347\211\231/\347\251\272\347\233\256\345\275\225.txt" "b/NO24/\350\231\216\347\211\231/\347\251\272\347\233\256\345\275\225.txt"
new file mode 100644
index 0000000..e69de29
-- 
GitLab