From 6053433a5e77786eb7902af5dd8039f7c38da5e0 Mon Sep 17 00:00:00 2001
From: hjCodeCloud <7482185+hjcodecloud@user.noreply.gitee.com>
Date: Wed, 23 Jun 2021 14:48:15 +0800
Subject: [PATCH] =?UTF-8?q?=E6=89=8B=E6=9C=BA=E5=A3=81=E7=BA=B8=E6=8A=93?=
 =?UTF-8?q?=E5=8F=96?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 NO8/index.py | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)
 create mode 100644 NO8/index.py

diff --git a/NO8/index.py b/NO8/index.py
new file mode 100644
index 0000000..a0b37b5
--- /dev/null
+++ b/NO8/index.py
@@ -0,0 +1,54 @@
+import requests
+import re
+import threading
+
+
+headers = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36"}
+
+# 循环获取 URL
+
+
+def get_image(base_url):
+
+    res = requests.get(
+        url=base_url, headers=headers)
+
+    if res is not None:
+        html = res.text
+
+        pattern = re.compile(
+            '<img lazysrc="(.*?)" lazysrc2x=".*?" width="221" height="362" alt=".*?" title="(.*?)"')
+        match_list = pattern.findall(html)
+        for url, title in match_list:
+            save_image(url[:url.find('jpg')+3], title)
+
+        print(match_list)
+
+
+def save_image(url, title):
+    try:
+        print(f"{title} - {url}")
+        res = requests.get(url=url, headers=headers)
+
+        if res is not None:
+            html = res.content
+
+            with open(f"images/{title}.jpg", "wb+") as f:
+                f.write(res.content)
+    except Exception as e:
+        print(e)
+
+
+if __name__ == '__main__':
+    num = 0
+    # 最多开启5个线程
+    semaphore = threading.BoundedSemaphore(5)
+    for index in range(189):
+        t = threading.Thread(target=get_image, args=(
+            f"https://www.3gbizhi.com/sjbz/index_{index}.html",))
+        t.start()
+    while threading.active_count() != 1:
+        pass
+    else:
+        print('所有线程运行完毕')
-- 
GitLab