From cddb5567235937e4d3a03b9e4bdd93039c87bd96 Mon Sep 17 00:00:00 2001
From: pnth2uekf <707689196@qq.com>
Date: Sat, 1 Jun 2024 18:02:15 +0800
Subject: [PATCH] ADD file via upload

---
 sousuo.py | 94 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 94 insertions(+)
 create mode 100644 sousuo.py

diff --git a/sousuo.py b/sousuo.py
new file mode 100644
index 0000000..7093e5f
--- /dev/null
+++ b/sousuo.py
@@ -0,0 +1,94 @@
+# 导入数据请求模块 --> 第三方模块, 需要安装
+import requests
+# 导入正则表达式模块 --> 内置模块, 不需要安装
+import re
+from bs4 import BeautifulSoup
+# 导入数据解析模块 --> 第三方模块, 需要安装
+import parsel
+# 导入文件操作模块 --> 内置模块, 不需要安装
+import os
+
+def get_response(html_url):
+    # 模拟浏览器 headers 请求头
+    headers = {
+        # user-agent 用户代理 表示浏览器基本身份信息
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36 Edg/124.0.0.0'
+    }
+    response = requests.get(url=html_url, headers=headers)
+    return response
+def get_list_url(html_url):
+    # 调用发送请求函数
+    html_data = get_response(html_url).text
+    # 提取小说名字
+    name = re.findall('<h1>(.*?)</h1>', html_data)[0]
+    # 提取章节url
+    soup = BeautifulSoup(html_data, 'html.parser')
+    link_tags = soup.find_all('dd')
+    url_list = []
+    for tag in link_tags:
+        if tag.find('a'):
+            url_list.append(tag.find('a')['href'])
+    return name, url_list
+def get_content(html_url):
+    # 调用发送请求函数
+    html_data = get_response(html_url).text
+    soup = BeautifulSoup(html_data, 'html.parser')
+    # 提取标题
+    title_tag = soup.find('h1', class_='wap_none')
+    if title_tag:
+        title = title_tag.text.strip()
+    else:
+        title = "未找到标题"
+    # 提取内容
+    content_tag = soup.find('div', id='chaptercontent')
+    if content_tag:
+        content = content_tag.text.strip().replace('<br>', '\n')
+    else:
+        content = "未找到内容"
+    return title, content
+def save(name, title, content):
+    # 自动创建一个文件夹
+    file = f'{name}\\'
+    if not os.path.exists(file):
+        os.mkdir(file)
+    with open(file + title + '.txt', mode='a', encoding='utf-8') as f:
+        # 写入内容
+        f.write(title)
+        f.write('\n')
+        f.write(content)
+        f.write('\n')
+    print(title, '已经保存')
+def get_novel_id(html_url):
+    # 调用发送请求函数
+    novel_data = get_response(html_url=html_url).text
+    selector = parsel.Selector(novel_data)
+    href = selector.css('.blocks a::attr(href)').getall()
+    return href
+
+def search(word):
+    search_url = f'https://www.biqugen.net/modules/article/search.php?searchkey={word}'
+    search_data = get_response(html_url=search_url).text
+    selector = parsel.Selector(search_data)
+    lis = selector.css('.grid tr')
+    for li in lis:
+        name = li.css('td.odd a::text').get()
+        novel_id = li.css('td.odd a::attr(href)').get().split('/')[-2]
+        writer = li.css('td.odd:nth-child(2)::text').get()
+        print(name, novel_id, writer)
+
+
+
+def main(home_url):
+    href = get_novel_id(html_url=home_url)
+    for novel_id in href:
+        novel_url = f'https://www.biqugen.net{novel_id}'
+        name, url_list = get_list_url(html_url=novel_url)
+        print(name, url_list)
+        for url in url_list:
+            index_url = 'https://www.biqugen.net/' + url
+            title, content = get_content(html_url=index_url)
+            save(name, title, content)
+
+if __name__ == '__main__':
+    word = input('请输入你搜索的小说名：')
+    search(word)
\ No newline at end of file