test

test/DrissiontionPage学习/音频下载/get_aa.py

@@ -0,0 +1,33 @@
+from DrissionPage import ChromiumPage
+import requests
+import re
+
+
+# page = ChromiumPage()
+#
+# page.get('https://www.pingshu5.net/pbook/sgyy112h/')
+# save_dir = "三国演义_评书"
+# # 先定位到包含所有章节的父元素
+# parent_ele = page.ele('@class=book-list clearfix')
+# # 再获取父元素下所有的a标签
+# a_list = parent_ele.eles('tag:a')
+# print(f"共找到 {len(a_list)} 个章节")
+#
+# for a in a_list:
+#     herf = a.link
+#     text = a.text
+#     print(f'开始下载:{text},下载地址:{herf}')
+#     html = requests.get(url=herf).text
+#     get_url = re.findall('<source rel="external nofollow" src="(.*?)" type="audio/mpeg" />', html)[0]
+#     with open(f'{save_dir}/{text}.mp3','wb') as f:
+#         f.write(requests.get(url = get_url).content)
+#     print(f'{text} 下载完成')
+
+headers = {
+    "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",  # 优先简体中文，其次中文、英文
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
+}
+
+html = requests.get('https://www.pingshu5.net/pbook/sgyy112h/',headers=headers)
+html.encoding = 'utf-8'
+html = html.text