刚刚都传——逆向版本上传——2023/10/20

ganggangdouchuan/ganggangdouchuan_main/run_ganggangdouchuan_recommend.py

@@ -1,33 +1,175 @@
 # -*- coding: utf-8 -*-
-# @Author: wangkun
-# @Time: 2023/4/13
+# @Author: luojunhui
+# @Time: 2023/10/20
 import argparse
-import os
-import sys
-import time
+import random
+
+from mq_http_sdk.mq_client import *
+from mq_http_sdk.mq_consumer import *
+from mq_http_sdk.mq_exception import MQExceptionBase
+
 sys.path.append(os.getcwd())
 from common.common import Common
-from ganggangdouchuan.ganggangdouchuan_recommend.ganggangdouchuan_recommend import GanggangdouchuanRecommend
+from common.public import get_consumer, ack_message, task_fun_mq, get_rule_from_mysql
+from common.scheduling_db import MysqlHelper
+from ganggangdouchuan.ganggangdouchuan_recommend import GGDCScheduling
+
+
+class GGDCMain:
+    @classmethod
+    def main(cls, log_type, crawler, topic_name, group_id, env):
+        consumer = get_consumer(topic_name, group_id)
+        # 长轮询表示如果Topic没有消息，则客户端请求会在服务端挂起3秒，3秒内如果有消息可以消费则立即返回响应。
+        # 长轮询时间3秒（最多可设置为30秒）。
+        wait_seconds = 30
+        # 一次最多消费3条（最多可设置为16条）。
+        batch = 1
+        Common.logger(log_type, crawler).info(
+            f'{10 * "="}Consume And Ack Message From Topic{10 * "="}\n'
+            f"WaitSeconds:{wait_seconds}\n"
+            f"TopicName:{topic_name}\n"
+            f"MQConsumer:{group_id}"
+        )
+        Common.logging(
+            log_type,
+            crawler,
+            env,
+            f'{10 * "="}Consume And Ack Message From Topic{10 * "="}\n'
+            f"WaitSeconds:{wait_seconds}\n"
+            f"TopicName:{topic_name}\n"
+            f"MQConsumer:{group_id}",
+        )
+        while True:
+            try:
+                # 长轮询消费消息。
+                recv_msgs = consumer.consume_message(batch, wait_seconds)
+                for msg in recv_msgs:
+                    Common.logger(log_type, crawler).info(
+                        f"Receive\n"
+                        f"MessageId:{msg.message_id}\n"
+                        f"MessageBodyMD5:{msg.message_body_md5}\n"
+                        f"MessageTag:{msg.message_tag}\n"
+                        f"ConsumedTimes:{msg.consumed_times}\n"
+                        f"PublishTime:{msg.publish_time}\n"
+                        f"Body:{msg.message_body}\n"
+                        f"NextConsumeTime:{msg.next_consume_time}\n"
+                        f"ReceiptHandle:{msg.receipt_handle}\n"
+                        f"Properties:{msg.properties}"
+                    )
+                    Common.logging(
+                        log_type,
+                        crawler,
+                        env,
+                        f"Receive\n"
+                        f"MessageId:{msg.message_id}\n"
+                        f"MessageBodyMD5:{msg.message_body_md5}\n"
+                        f"MessageTag:{msg.message_tag}\n"
+                        f"ConsumedTimes:{msg.consumed_times}\n"
+                        f"PublishTime:{msg.publish_time}\n"
+                        f"Body:{msg.message_body}\n"
+                        f"NextConsumeTime:{msg.next_consume_time}\n"
+                        f"ReceiptHandle:{msg.receipt_handle}\n"
+                        f"Properties:{msg.properties}",
+                    )
+                    # ack_mq_message
+                    ack_message(
+                        log_type=log_type,
+                        crawler=crawler,
+                        recv_msgs=recv_msgs,
+                        consumer=consumer,
+                    )
+
+                    # 处理爬虫业务
+                    task_dict = task_fun_mq(msg.message_body)["task_dict"]
+                    rule_dict = task_fun_mq(msg.message_body)["rule_dict"]
+                    task_id = task_dict["id"]
+                    select_user_sql = (
+                        f"""select * from crawler_user_v3 where task_id={task_id}"""
+                    )
+                    user_list = MysqlHelper.get_values(
+                        log_type, crawler, select_user_sql, env, action=""
+                    )
+                    our_uid_list = []
+                    for user in user_list:
+                        our_uid_list.append(user["uid"])
+                    our_uid = random.choice(our_uid_list)
+                    Common.logger(log_type, crawler).info(f"调度任务:{task_dict}")
+                    Common.logging(log_type, crawler, env, f"调度任务:{task_dict}")
+                    Common.logger(log_type, crawler).info(f"抓取规则:{rule_dict}")
+                    Common.logging(log_type, crawler, env, f"抓取规则:{rule_dict}")
+                    Common.logger(log_type, crawler).info(f"用户列表:{user_list}\n")
+                    Common.logging(log_type, crawler, env, f"用户列表:{user_list}\n")
+                    Common.logger(log_type, crawler).info(
+                        f'开始抓取:{task_dict["taskName"]}\n'
+                    )
+                    Common.logging(
+                        log_type, crawler, env, f'开始抓取:{task_dict["taskName"]}\n'
+                    )
+                    new_r = get_rule_from_mysql(
+                        task_id=task_id, log_type=log_type, crawler=crawler, env=env
+                    )
+                    r_d = {}
+                    for item in new_r:
+                        for k, val in item.items():
+                            r_d[k] = val
+                    Common.logger(log_type, crawler).info(f"抓取规则:{r_d}")
+                    Common.logging(log_type, crawler, env, f"抓取规则:{r_d}")
+                    # 初始化
+                    GGDC = GGDCScheduling(
+                        log_type=log_type,
+                        crawler=crawler,
+                        env=env,
+                        rule_dict=r_d,
+                        our_uid=our_uid,
+                    )
+                    for i in range(20):
+                        if GGDC.download_count >= int(
+                            rule_dict.get("videos_cnt", {}).get("min", 10)
+                        ):
+                            GGDC.download_count = 0
+                            break
+                        else:
+                            GGDC.get_videoList(page_id=i + 1)
+                            time.sleep(60)
+                    Common.logger(log_type, crawler).info("抓取一轮结束\n")
+                    Common.logging(log_type, crawler, env, "抓取一轮结束\n")
 
+            except MQExceptionBase as err:
+                # Topic中没有消息可消费。
+                if err.type == "MessageNotExist":
+                    Common.logger(log_type, crawler).info(
+                        f"No new message! RequestId:{err.req_id}\n"
+                    )
+                    Common.logging(
+                        log_type,
+                        crawler,
+                        env,
+                        f"No new message! RequestId:{err.req_id}\n",
+                    )
+                    continue
 
-def main(log_type, crawler, env):
-    Common.logger(log_type, crawler).info('开始抓取:刚刚都传小程序\n')
-    Common.logging(log_type, crawler, env, '开始抓取:刚刚都传小程序\n')
-    ganggangdouchuan_start_time = int(time.time())
-    GanggangdouchuanRecommend.start_wechat(log_type, crawler, env)
-    Common.del_logs(log_type, crawler)
-    Common.logger(log_type, crawler).info('抓取完一轮\n')
-    Common.logging(log_type, crawler, env, '抓取完一轮\n')
-    ganggangdouchuan_end_time = int(time.time())
-    ganggangdouchuan_duration = ganggangdouchuan_end_time - ganggangdouchuan_start_time
-    Common.logger(log_type, crawler).info(f"duration {ganggangdouchuan_duration}")
-    Common.logging(log_type, crawler, env, f"duration {ganggangdouchuan_duration}")
+                Common.logger(log_type, crawler).info(
+                    f"Consume Message Fail! Exception:{err}\n"
+                )
+                Common.logging(
+                    log_type, crawler, env, f"Consume Message Fail! Exception:{err}\n"
+                )
+                time.sleep(2)
+                continue
 
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()  ## 新建参数解释器对象
-    parser.add_argument('--log_type', type=str)  ## 添加参数,注明参数类型
-    parser.add_argument('--crawler')  ## 添加参数
-    parser.add_argument('--env')  ## 添加参数
+    parser.add_argument("--log_type", type=str)  ## 添加参数,注明参数类型
+    parser.add_argument("--crawler")  ## 添加参数
+    parser.add_argument("--topic_name")  ## 添加参数
+    parser.add_argument("--group_id")  ## 添加参数
+    parser.add_argument("--env")  ## 添加参数
     args = parser.parse_args()  ### 参数赋值，也可以通过终端赋值
-    main(log_type=args.log_type, crawler=args.crawler, env=args.env)
+    GGDCMain.main(
+        log_type=args.log_type,
+        crawler=args.crawler,
+        topic_name=args.topic_name,
+        group_id=args.group_id,
+        env=args.env,
+    )

ganggangdouchuan/ganggangdouchuan_recommend/__init__.py

@@ -1,3 +1 @@
-# -*- coding: utf-8 -*-
-# @Author: wangkun
-# @Time: 2023/4/13
+from .ganggangdouchuan_recommend2 import GGDCScheduling

ganggangdouchuan/ganggangdouchuan_recommend/ganggangdouchuan_recommend2.py

@@ -0,0 +1,272 @@
+# -*- coding: utf-8 -*-
+# @Author: luojunhui
+# @Time: 2023/10/10
+import json
+import os
+import random
+import sys
+import time
+import requests
+from Crypto.Cipher import AES
+from Crypto.Hash import MD5
+from Crypto.Util.Padding import pad, unpad
+from base64 import b64encode, b64decode
+
+from common.mq import MQ
+
+sys.path.append(os.getcwd())
+from common.common import Common
+from common.scheduling_db import MysqlHelper
+from common.public import get_config_from_mysql, download_rule_v2
+
+proxies = {"http": None, "https": None}
+
+
+def clean_title(strings):
+    return (
+        strings.strip()
+        .replace("\n", "")
+        .replace("/", "")
+        .replace("\r", "")
+        .replace("#", "")
+        .replace(".", "。")
+        .replace("\\", "")
+        .replace("&NBSP", "")
+        .replace(":", "")
+        .replace("*", "")
+        .replace("？", "")
+        .replace("?", "")
+        .replace('"', "")
+        .replace("<", "")
+        .replace(">", "")
+        .replace("|", "")
+        .replace(" ", "")
+        .replace('"', "")
+        .replace("'", "")
+    )
+
+
+def decrypt(a, e, n):
+    e = MD5.new(e.encode()).hexdigest()
+    key = e[16:].encode()
+    iv = e[:16].encode()
+
+    cipher = AES.new(key, AES.MODE_CBC, iv)
+
+    if n:
+        encrypted_data = b64decode(a)
+        # print(encrypted_data)
+        decrypted_data = unpad(cipher.decrypt(encrypted_data), AES.block_size)
+        return decrypted_data.decode()
+    else:
+        padded_data = pad(a.encode(), AES.block_size)
+        encrypted_data = cipher.encrypt(padded_data)
+        return b64encode(encrypted_data).decode()
+
+
+def find_tencent_url(tx_vid):
+    headers = {
+        "Host": "h5vv.video.qq.com",
+        "xweb_xhr": "1",
+        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36 MicroMessenger/6.8.0(0x16080000) NetType/WIFI MiniProgramEnv/Mac MacWechat/WMPF XWEB/30817",
+        "Content-Type": "application/x-www-form-urlencoded",
+        "Accept": "*/*",
+        "Sec-Fetch-Site": "cross-site",
+        "Sec-Fetch-Mode": "cors",
+        "Sec-Fetch-Dest": "empty",
+        "Referer": "https://servicewechat.com/wx5fcd817f3f80aece/3/page-frame.html",
+        "Accept-Language": "en",
+    }
+
+    video_id = tx_vid
+
+    url = "https://h5vv.video.qq.com/getinfo?vid={}&platform=101001&charge=0&otype=json&defn=shd".format(
+        video_id
+    )
+
+    response = requests.get(url, headers=headers)
+
+    result = json.loads(response.text.replace("QZOutputJson=", "")[:-1])
+    vl = result["vl"]["vi"][0]
+    key = vl["fvkey"]
+    name = vl["fn"]
+    folder = vl["ul"]["ui"][0]["url"]
+    url = folder + name + "?vkey=" + key
+    return url
+
+
+class GGDCScheduling:
+    def __init__(self, log_type, crawler, rule_dict, env, our_uid):
+        self.platform = "刚刚都传"
+        self.log_type = log_type
+        self.crawler = crawler
+        self.rule_dict = rule_dict
+        self.env = env
+        self.our_uid = our_uid
+        self.mq = MQ(topic_name="topic_crawler_etl_" + self.env)
+        self.download_count = 0
+
+    def repeat_video(self, video_id):
+        sql = f""" select * from crawler_video where platform in ("{self.crawler}","{self.platform}") and out_video_id="{video_id}"; """
+        repeat_video = MysqlHelper.get_values(
+            self.log_type, self.crawler, sql, self.env
+        )
+        return len(repeat_video)
+
+    # 获取视频id_list
+    def get_videoList(self, page_id):
+        time.sleep(random.randint(5, 10))
+        url = "https://ganggangdouchuan2.mengniu99.com/api/getcatevideos"
+        params = {
+            "cateid": "video",
+            "page": page_id,
+            "timeline": 0,
+            "version": "9.0.2",
+            # "timestamp": 1697700674000,
+            # "openid": "oNnpe5SwkfGtD5aJAaRbsIKIEdjc",
+        }
+        headers = {
+            "Host": "ganggangdouchuan2.mengniu99.com",
+            # "Authorization": "oNnpe5SwkfGtD5aJAaRbsIKIEdjc",
+            "xweb_xhr": "1",
+            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36 MicroMessenger/6.8.0(0x16080000) NetType/WIFI MiniProgramEnv/Mac MacWechat/WMPF XWEB/30817",
+            # "Sign": "88ab143a9401ebac3525562073248231",
+            "Content-Type": "application/json",
+            "Accept": "*/*",
+            "Sec-Fetch-Site": "cross-site",
+            "Sec-Fetch-Mode": "cors",
+            "Sec-Fetch-Dest": "empty",
+            "Referer": "https://servicewechat.com/wx5fcd817f3f80aece/3/page-frame.html",
+            "Accept-Language": "en",
+        }
+        response = requests.get(url, headers=headers, params=params)
+        while True:
+            try:
+                decrypted_data = decrypt(
+                    response.json()["data"], response.json()["_yyy"], True
+                )
+                result = json.loads(decrypted_data)
+                break
+            except:
+                print("编码不对,解密失败, 等待10秒钟")
+                time.sleep(10)
+
+        if "totalCount" not in result or response.status_code != 200:
+            Common.logger(self.log_type, self.crawler).info(
+                f"get_videoList:{response.text}\n"
+            )
+            Common.logging(
+                self.log_type,
+                self.crawler,
+                self.env,
+                f"get_videoList:{response.text}\n",
+            )
+            return
+        elif len(result["videos"]) == 0:
+            Common.logger(self.log_type, self.crawler).info(f"没有更多数据啦~\n")
+            Common.logging(self.log_type, self.crawler, self.env, f"没有更多数据啦~\n")
+            return
+        else:
+            data_list = result["videos"]
+            for video_obj in data_list:
+                try:
+                    self.process_video_obj(video_obj)
+                except Exception as e:
+                    Common.logger(self.log_type, self.crawler).error(f"抓取单条视频异常:{e}\n")
+                    Common.logging(
+                        self.log_type, self.crawler, self.env, f"抓取单条视频异常:{e}\n"
+                    )
+
+    def process_video_obj(self, video_obj):
+        video_id = video_obj.get("videoid", 0)
+        video_title = clean_title(video_obj.get("title", "no title"))
+        video_time = video_obj.get("v_time", 0)
+        publish_time_stamp = int(time.time())
+        publish_time_str = time.strftime(
+            "%Y-%m-%d %H:%M:%S", time.localtime(publish_time_stamp)
+        )
+        user_name = video_obj["nickname"]
+        video_dict = {
+            "video_title": video_title,
+            "video_id": video_id,
+            "duration": video_time,
+            "play_cnt": 0,
+            "like_cnt": 0,
+            "comment_cnt": 0,
+            "share_cnt": 0,
+            "user_name": user_name,
+            "publish_time_stamp": publish_time_stamp,
+            "publish_time_str": publish_time_str,
+            "video_width": 0,
+            "video_height": 0,
+            "profile_id": 0,
+            "profile_mid": 0,
+            "cover_url": video_obj["cover"],
+            "session": f"ganggangdouchuan-{int(time.time())}",
+        }
+        for k, v in video_dict.items():
+            Common.logger(self.log_type, self.crawler).info(f"{k}:{v}")
+        Common.logging(self.log_type, self.crawler, self.env, f"{video_dict}")
+        # 过滤无效视频
+        if video_title == "" or video_dict["video_id"] == "":
+            Common.logger(self.log_type, self.crawler).info("无效视频\n")
+            Common.logging(self.log_type, self.crawler, self.env, "无效视频\n")
+            # 抓取基础规则过滤
+        elif (
+            download_rule_v2(
+                log_type=self.log_type,
+                crawler=self.crawler,
+                video_dict=video_dict,
+                rule_dict=self.rule_dict,
+            )
+            is False
+        ):
+            Common.logger(self.log_type, self.crawler).info("不满足抓取规则\n")
+            Common.logging(self.log_type, self.crawler, self.env, "不满足抓取规则\n")
+        elif (
+            any(
+                str(word) if str(word) in video_dict["video_title"] else False
+                for word in get_config_from_mysql(
+                    log_type=self.log_type,
+                    source=self.crawler,
+                    env=self.env,
+                    text="filter",
+                    action="",
+                )
+            )
+            is True
+        ):
+            Common.logger(self.log_type, self.crawler).info("已中过滤词\n")
+            Common.logging(self.log_type, self.crawler, self.env, "已中过滤词\n")
+        elif self.repeat_video(video_dict["video_id"]) != 0:
+            Common.logger(self.log_type, self.crawler).info("视频已下载\n")
+            Common.logging(self.log_type, self.crawler, self.env, "视频已下载\n")
+        else:
+            video_dict["out_user_id"] = video_dict["profile_id"]
+            video_dict["platform"] = self.crawler
+            video_dict["strategy"] = self.log_type
+            video_dict["out_video_id"] = str(video_dict["video_id"])
+            video_dict["width"] = video_dict["video_width"]
+            video_dict["height"] = video_dict["video_height"]
+            video_dict["crawler_rule"] = json.dumps(self.rule_dict)
+            video_dict["user_id"] = self.our_uid
+            video_dict["publish_time"] = video_dict["publish_time_str"]
+            video_dict["video_url"] = find_tencent_url(video_obj["txvid"])
+            video_dict["avatar_url"] = video_obj["avatarurl"]
+            video_dict["cover_url"] = video_obj["cover"]
+            # print(json.dumps(video_dict, ensure_ascii=False, indent=4))
+            self.download_count += 1
+            self.mq.send_msg(video_dict)
+
+
+if __name__ == "__main__":
+    ZL = GGDCScheduling(
+        log_type="recommend",
+        crawler="ggdc",
+        rule_dict={},
+        our_uid="luojunhuihaoshuai",
+        env="dev",
+    )
+    for i in range(5):
+        ZL.get_videoList(page_id=i + 1)
+        print(ZL.download_count)