add some scripts.

scripts/iafd/distributors_list_fetch.py

@@ -0,0 +1,192 @@
+"""
+Script Name: 
+Description: 从 https://www.iafd.com 上获取信息。利用cloudscraper绕过cloudflare
+    detail_fetch.py 从本地已经保存的列表数据,逐个拉取详情,并输出到文件。
+    list_fetch_astro.py 按照星座拉取数据,获得演员的信息列表。数据量适中,各详细字段较全
+    list_fetch_birth.py 按照生日拉取数据,获得演员的信息列表。数据量适中,各详细字段较全
+    list_fetch_ethnic.py 按照人种拉取数据,获得演员的信息列表。数据量大,但详细字段很多无效的
+    list_merge.py 上面三个列表的数据,取交集,得到整体数据。
+    iafd_scrape.py 借助 https://github.com/stashapp/CommunityScrapers 实现的脚本,可以输入演员的 iafd链接,获取兼容 stashapp 格式的数据。（作用不大,因为国籍、照片等字段不匹配）
+
+    html_format.py 负责读取已经保存的html目录, 提取信息,格式化输出。
+    data_merge.py 负责合并数据,它把从 iafd, javhd, thelordofporn 以及搭建 stashapp, 从上面更新到的演员数据(需导出)进行合并；
+    stashdb_merge.py 负责把从stashapp中导出的单个演员的json文件, 批量合并并输出; 通常我们需要把stashapp中导出的批量文件压缩并传输到data/tmp目录,解压后合并
+    从而获取到一份完整的数据列表。
+
+Author: [Your Name]
+Created Date: YYYY-MM-DD
+Last Modified: YYYY-MM-DD
+Version: 1.0
+
+Modification History:
+    - YYYY-MM-DD [Your Name]: 
+    - YYYY-MM-DD [Your Name]: 
+    - YYYY-MM-DD [Your Name]: 
+"""
+
+import cloudscraper
+import json
+import time
+import csv
+from bs4 import BeautifulSoup
+import logging
+import config
+
+config.setup_logging()
+
+# 定义基础 URL 和可变参数
+host_url = "https://www.iafd.com"
+base_url = f"{host_url}/distrib.rme/distrib="
+dist_list_url = f'{base_url}/distrib.asp'
+
+distr_map = {
+    6812 : 'nubilefilms.com',
+    8563 : 'teenmegaworld network',
+    6779 : 'x-art.com',
+    7133 : 'tushy.com',
+    6496 : 'blacked.com',
+    7758 : 'vixen.com',
+    6791 : 'teamskeet.com',
+    12454: 'vip4k.com',
+    13541: 'wow network',
+    9702 : 'cum4k.com',
+    6778 : 'tiny4k.com',
+    12667: 'anal4k.com',
+    7419 : 'exotic4k.com',
+    13594: 'facials4k.com',
+    13633: 'mom4k.com',
+    12335: 'slim4k.com',
+    16709: 'strippers4k.com',
+
+}
+
+# 设置 headers 和 scraper
+headers = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
+}
+scraper = cloudscraper.create_scraper()
+
+# 结果路径
+res_dir = './result'
+all_data = []
+
+# 网络请求并解析 HTML
+def fetch_page(url):
+    try:
+        response = scraper.get(url, headers=headers)
+        response.raise_for_status()
+        return response.text
+    except Exception as e:
+        logging.error(f"Failed to fetch {url}: {e}")
+        return None
+
+# 解析 HTML 内容，提取需要的数据
+def parse_page(html, name):
+    soup = BeautifulSoup(html, "html.parser")
+    table = soup.find("table", id="distable")
+
+    if not table:
+        logging.warning(f"Warning: No 'distable' table found in {name}")
+        return None
+    
+    # 找到thead并跳过
+    thead = table.find('thead')
+    if thead:
+        thead.decompose()  # 去掉thead部分，不需要解析
+
+    # 现在只剩下tbody部分
+    tbody = table.find('tbody')
+    rows = tbody.find_all('tr') if tbody else []
+
+    global all_data
+    for row in rows:
+        cols = row.find_all('td')
+        if len(cols) >= 5:
+            title = cols[0].text.strip()
+            label = cols[1].text.strip()
+            year = cols[2].text.strip()
+            rev = cols[3].text.strip()
+            a_href = cols[0].find('a')
+            href = host_url + a_href['href'] if a_href else ''
+
+            all_data.append({
+                'distributors': name,
+                'title': title,
+                'label': label,
+                'year': year,
+                'rev': rev,
+                'href': href
+            })
+    return soup
+
+# 处理翻页,星座的无需翻页
+def handle_pagination(soup, astro):
+    return None
+
+# 获取列表页
+def process_list_gage():
+    global distr_map
+
+    logging.info(f"Fetching data for {dist_list_url} ...")
+    select_element = None
+    while True:
+        html = fetch_page(dist_list_url)
+        if html:
+            soup = BeautifulSoup(html, "html.parser")
+            select_element = soup.find('select', {'name': 'Distrib'})
+            if select_element :
+                break
+            else:
+                logging.info(f"wrong html content. retring {dist_list_url} ...")
+        else:
+            logging.info(f"wrong html content. retring {dist_list_url} ...")
+
+    if not select_element:
+        return None
+    
+    options = select_element.find_all('option')
+    for option in options:
+        value = option.get('value')  # 获取 value 属性
+        text = option.text.strip()   # 获取文本内容
+        distr_map[int(value)] = text
+    logging.info(f'fetch {dist_list_url} succ. total distributors: {len(distr_map)}')
+    return True
+
+# 主逻辑函数：循环处理每个种族
+def process_main_data():
+    for dis_key, dis_name in distr_map.items():
+        url = base_url + str(dis_key)
+        next_url = url
+        logging.info(f"Fetching data for {dis_name}, url {url} ...")
+
+        while next_url:
+            html = fetch_page(next_url)
+            if html:
+                soup = parse_page(html, dis_name)
+                if soup:
+                    next_url = handle_pagination(soup, dis_name)
+                else:
+                    logging.info(f"wrong html content. retring {next_url} ...")
+                # 定期保存结果
+                save_data()
+                time.sleep(2)  # 控制访问频率
+            else:
+                logging.info(f"Retrying {next_url} ...")
+                time.sleep(5)  # 等待后再重试
+
+# 保存到文件
+def save_data():
+    with open(f'{res_dir}/distributors.json', 'w', encoding='utf-8') as json_file:
+        json.dump(all_data, json_file, indent=4, ensure_ascii=False)
+    
+    with open(f'{res_dir}/distributors.csv', 'w', newline='', encoding='utf-8') as csv_file:
+        writer = csv.DictWriter(csv_file, fieldnames=['distributors', 'title', 'label', 'year', 'rev', 'href'])
+        writer.writeheader()
+        writer.writerows(all_data)
+
+# 执行主逻辑
+if __name__ == '__main__':
+    #process_list_gage()
+    process_main_data()
+    save_data()
+    logging.info("Data fetching and saving completed.")