整理文件夹

cookie.txt

@@ -0,0 +1 @@
+Hm_lvt_7a3960b6f067eb0085b7f96ff5e660b0=1690080220,1690550836,1690723621,1690809059; ndut_fmt=2F3F7209152B005542DB9E27E1FE8B25A229DCC706598E1B99139109B3AD5791; BDCLND=Kiz1b8Bpv31XBFDJNdGFjZSNEpvCREEMgiHA5oAF99k%3D; BDUSS=3dlMEhZLWtLS2tGeVh2T1ozYWtYaXdFTWV6QnRrYzByMEwzd2hWWmxkamd4dk5pRVFBQUFBJCQAAAAAAAAAAAEAAADgajfycm9nZXJzdW4wOTAxAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAOA5zGLgOcxid; BIDUPSID=2947C9BCCF77B5D4BFC420C602BE3DF5; PSTM=1658846657; ZFY=0Vc50oTr7EmlM6WxzWE2Eewo0ltT5VQJ2KG9s8DcdoY:C; MCITY=-131%3A; STOKEN=d598c65d443486ba06db34f988e6ac8d108c6b2e4f4eae47aeec796b8c487453; BAIDUID=8DC7F291FA0638DF89C98F0178FCDC7C:FG=1; BAIDUID_BFESS=8DC7F291FA0638DF89C98F0178FCDC7C:FG=1; PANWEB=1; newlogin=1; csrfToken=2r7JSCtVulGN3eOExz3JqsxP; PANPSC=12925419710669722059%3AKkwrx6t0uHBNjb%2BA%2BPLlBZgtJeEFa7WQw1jWL8y1tqu8ztnSQmWL1wZuq6kOUHWChFbm%2BExtunGiz1cJOClRr8ZIzuhpmLh6b55KeZe4CQBn3K3RJ8ZwedL9vR6DsgcTu1tPRVPr6y7%2FwyO%2B4eG7s0I0NZhR03fFuueAr2t%2FRhNXpcvfoZtUp%2B4PuTzNr1rr; ab_sr=1.0.1_NDE5NTY0NjYxYjNjZmVjZmQ2YTY1YjYzMjFlY2E5MGViZWI2MWY5MzA1Yzk4N2M1YzM3YmFlZmM2MmM1NmNmYjgzYTk4NWQxNzdiZWQxZTAzN2RlYjQ2NmI1NjAzNTAwNmJjNjNlZGFkN2JmNTUxNDMzNmRkM2RkZWVhZTZhMTM4ZjA3ZjJlMTAxYTc2MTk2YmM0YTA5OGUzMWIzNzE5Yjg0MTFkNzdjOThhMjA5ZDVhODczOTZiYzM2ZmEzZjhk

db.py

@@ -0,0 +1,43 @@
+import pymysql
+from pymysql.cursors import DictCursor
+import datetime
+
+db_config = {
+    'host': '192.168.66.101',
+    'user': 'root',
+    'password': 'Sxzgx1209',
+    'database': 'scrapy'
+}
+
+
+class DbAction:
+    def __init__(self, end_date='today'):
+        self.conn = pymysql.Connection(**db_config)
+        self.cursor = self.conn.cursor(cursor=DictCursor)
+        self.date_list = self.get_date_list(end_date)
+
+    def get_db_data(self):
+        query_sql = f"SELECT h.id, h.cate, h.date, h.`name`, h.save_link, h.`code`, h.unzip_pwd FROM scrapyh h WHERE h.date IN ({self.date_list});"
+        self.cursor.execute(query_sql)
+        return self.cursor.fetchall()
+
+    @staticmethod
+    def get_date_list(_end_date):
+        date_list = []
+        if _end_date == 'today':
+            date_list.append(f"'{datetime.date.strftime(datetime.date.today(), '%Y-%m-%d')}'")
+        else:
+            start_date = datetime.datetime.today()
+            end_date = datetime.datetime.strptime(_end_date, '%Y-%m-%d')
+            delta = datetime.timedelta(days=1)
+            while start_date > end_date:
+                date_list.append(f"'{datetime.datetime.strftime(start_date, '%Y-%m-%d')}'")
+                start_date = start_date - delta
+        print(date_list)
+        return ','.join(date_list)
+
+
+if __name__ == '__main__':
+    db_action = DbAction('2023-07-28')
+    result = db_action.get_db_data()
+    print(result)

req.py

@@ -0,0 +1,169 @@
+import os
+
+import requests
+import urllib3
+import random
+import re
+import time
+from retrying import retry
+
+urllib3.disable_warnings()
+
+# 静态变量
+BASE_URL = 'https://pan.baidu.com'
+ERROR_CODES = {
+    1: '链接失效，没获取到 shareid',
+    2: '链接失效，没获取到 user_id',
+    3: '链接失效，没获取到 fs_id',
+    '百度网盘-链接不存在': '链接失效，文件已经被删除或取消分享',
+    '百度网盘 请输入提取码': '链接错误，缺少提取码',
+    -9: '链接错误，提取码错误或验证已过期',
+    -62: '链接错误尝试次数过多，请手动转存或稍后再试',
+    105: '链接错误，链接格式不正确',
+    -4: '转存失败，无效登录。请退出账号在其他地方的登录',
+    -6: '转存失败，请用浏览器无痕模式获取 Cookie',
+    4: '转存失败，目录中已有同名文件或文件夹存在',
+    -8: '转存失败，目录中已有同名文件或文件夹存在',
+    12: '转存失败，转存文件数超过限制',
+    -7: '转存失败，秒传文件名有非法字符',
+    404: '转存失败，秒传无效',
+    31190: '转存失败，秒传未生效',
+    31039: '转存失败，秒传文件名冲突',
+    -10: '转存失败，容量不足',
+    20: '转存失败，容量不足',
+    0: '转存成功',
+}
+
+
+class ReqAction:
+    # 请求变量
+    request_header = {
+        'Host': 'pan.baidu.com',
+        'Connection': 'keep-alive',
+        'Upgrade-Insecure-Requests': '1',
+        'Sec-Fetch-Dest': 'document',
+        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
+        'Sec-Fetch-Site': 'same-site',
+        'Sec-Fetch-Mode': 'navigate',
+        'Referer': 'https://pan.baidu.com',
+        'Accept-Encoding': 'gzip, deflate, br',
+        'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-US;q=0.7,en-GB;q=0.6,ru;q=0.5',
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36',
+    }
+
+    def __init__(self):
+        # 会话配置
+        self.session = requests.Session()
+        self.bdstoken = None
+
+    def get_cookies(self):
+        with open('cookie.txt', 'r', encoding='utf-8') as f:
+            self.request_header['Cookie'] = f.readline()
+
+    # 获取bdstoken函数
+    @retry(stop_max_attempt_number=3, wait_fixed=random.randint(1000, 3000))
+    def get_bdstoken(self):
+        url = f'{BASE_URL}/api/gettemplatevariable?clienttype=0&app_id=250528&web=1&fields=[%22bdstoken%22,%22token%22,%22uk%22,%22isdocuser%22,%22servertime%22]'
+        response = self.session.get(url=url, headers=self.request_header, timeout=20, allow_redirects=True,
+                                    verify=False)
+        print(response.text)
+        return response.json()['errno'] if response.json()['errno'] != 0 else response.json()['result']['bdstoken']
+
+    # 获取目录列表函数
+    @retry(stop_max_attempt_number=5, wait_fixed=random.randint(1000, 3000))
+    def get_dir_list(self, dir_path):
+        url = f'{BASE_URL}/api/list?order=time&desc=1&showempty=0&web=1&page=1&num=1000&dir={dir_path}&bdstoken={self.bdstoken}'
+        response = self.session.get(url=url, headers=self.request_header, timeout=15, allow_redirects=False,
+                                    verify=False)
+        print(response.text)
+        return response.json()['errno'] if response.json()['errno'] != 0 else response.json()['list']
+
+    # 新建目录函数
+    @retry(stop_max_attempt_number=5, wait_fixed=random.randint(1000, 3000))
+    def create_dir(self, target_directory_name):
+        url = f'{BASE_URL}/api/create?a=commit&bdstoken={self.bdstoken}'
+        post_data = {'path': target_directory_name, 'isdir': '1', 'block_list': '[]', }
+        response = self.session.post(url=url, headers=self.request_header, data=post_data, timeout=15,
+                                     allow_redirects=False, verify=False)
+        print(response.text)
+        return response.json()['errno']
+
+    # 更新 cookie 函数
+    def update_cookie(self, bdclnd):
+        if 'BDCLND=' in self.request_header['Cookie']:
+            self.request_header['Cookie'] = re.sub(r'BDCLND=(\S+);?', f'BDCLND={bdclnd};',
+                                                   self.request_header['Cookie'])
+        else:
+            self.request_header['Cookie'] += f';BDCLND={bdclnd}'
+
+    # 验证提取码函数
+    @retry(stop_max_attempt_number=6, wait_fixed=1700)
+    def verify_pass_code(self, link_url, pass_code):
+        check_url = f'{BASE_URL}/share/verify?surl={link_url[25:48]}&bdstoken={self.bdstoken}&t={str(int(round(time.time() * 1000)))}&channel=chunlei&web=1&clienttype=0'
+        post_data = {'pwd': pass_code, 'vcode': '', 'vcode_str': '', }
+        response = self.session.post(url=check_url, headers=self.request_header, data=post_data, timeout=10,
+                                     allow_redirects=False, verify=False)
+        print(response.text)
+        return response.json()['errno'] if response.json()['errno'] != 0 else response.json()['randsk']
+
+    # 验证链接函数
+    @retry(stop_max_attempt_number=12, wait_fixed=1700)
+    def verify_links(self, link_url, pass_code):
+        if pass_code:
+            bdclnd = self.verify_pass_code(link_url, pass_code)
+            if isinstance(bdclnd, int):
+                return bdclnd
+            self.update_cookie(bdclnd)
+
+        response = self.session.get(url=link_url, headers=self.request_header, timeout=15, allow_redirects=True,
+                                    verify=False).content.decode("utf-8")
+        print(response)
+        shareid_list = re.findall('"shareid":(\\d+?),"', response)
+        user_id_list = re.findall('"share_uk":"(\\d+?)","', response)
+        fs_id_list = re.findall('"fs_id":(\\d+?),"', response)
+        info_title_list = re.findall('<title>(.+)</title>', response)
+
+        if not shareid_list:
+            return 1
+        elif not user_id_list:
+            return 2
+        elif not fs_id_list:
+            return info_title_list[0] if info_title_list else 3
+        else:
+            return [shareid_list[0], user_id_list[0], fs_id_list]
+
+    # 转存文件函数
+    @retry(stop_max_attempt_number=9, wait_fixed=random.randint(1000, 3000))
+    def transfer_files(self, verify_links_reason, target_directory_name):
+        url = f'{BASE_URL}/share/transfer?shareid={verify_links_reason[0]}&from={verify_links_reason[1]}&bdstoken={self.bdstoken}&channel=chunlei&web=1&clienttype=0'
+        post_data = {'fsidlist': f'[{",".join(i for i in verify_links_reason[2])}]',
+                     'path': f'/{target_directory_name}', }
+        response = self.session.post(url=url, headers=self.request_header, data=post_data, timeout=15,
+                                     allow_redirects=False, verify=False)
+        print(response.text)
+        return response.json()['errno']
+
+    def main(self):
+        base_dir = '/Temp/'
+        cate_dir = 'leshe/'
+        target_dir_name = '2'
+        target_dir = os.path.join(base_dir, cate_dir, target_dir_name)
+        print(target_dir)
+        # link_list = []
+        # self.get_cookies()
+        # self.bdstoken = self.get_bdstoken()
+        # dir_list = self.get_dir_list('/Temp/leshe')
+        # print([_dir['path'] for _dir in dir_list])
+        # if target_dir in [_dir['path'] for _dir in dir_list]:
+        #     print('找到了')
+        # # if dir_name and dir_name not in [_dir('path') for _dir in self.dir_list]:
+        # #     self.create_dir(r'/Temp/leshe/1')
+        # # 执行转存
+        # for link in link_list:
+        #     verified_links = self.verify_links(link[0], link[1])
+        #     self.transfer_files(verified_links, target_dir)
+
+
+if __name__ == '__main__':
+    req = ReqAction()
+    req.main()