Merge remote-tracking branch 'origin/master'

analysis/analysis.py

@@ -41,7 +41,7 @@ class Analysis(object):
 class Drawer(object):
     def __init__(self, json_obj):
         self.ori_data = json_obj
-        self.x_list = ["2023-11-{:02}".format(i) for i in range(1, 24)]
+        self.x_list = ["2023-11-{:02}".format(i) for i in range(1, 28)]
 
     def draw_line(self):
         line = Line()

zhuwanwufusu/zhuwanwufusu_main/run_zwwfs_recommend.py

@@ -83,7 +83,6 @@ def main(log_type, crawler, topic_name, group_id, env):
                 user_list = MysqlHelper.get_values(
                     log_type, crawler, select_user_sql, env, action=""
                 )
-                user_dict = random.choice(user_list)
                 AliyunLogger.logging(
                     code="1003",
                     platform=crawler,
@@ -102,7 +101,7 @@ def main(log_type, crawler, topic_name, group_id, env):
                     platform=crawler,
                     mode=log_type,
                     rule_dict=rule_dict,
-                    user_dict=user_dict,
+                    user_list=user_list,
                     env=env
                 )
                 main_process.schedule()

zhuwanwufusu/zhuwanwufusu_recommend/zwwfs_recommend.py

@@ -16,11 +16,11 @@ from zhuwanwufusu.crypt import AESCipher as AES
 
 
 class ZhuWanWuFuSuRecommend(object):
-    def __init__(self, platform, mode, rule_dict, user_dict, env):
+    def __init__(self, platform, mode, rule_dict, user_list, env):
         self.platform = platform
         self.mode = mode
         self.rule_dict = rule_dict
-        self.user_dict = user_dict
+        self.user_list = user_list
         self.env = env
         self.download_cnt = 0
         self.mq = MQ(topic_name="topic_crawler_etl_" + self.env)
@@ -167,6 +167,7 @@ class ZhuWanWuFuSuRecommend(object):
                 video_obj['playnum'])
         else:
             play_cnt = 0
+        our_user = random.choice(self.user_list)
         item = VideoItem()
         item.add_video_info("video_id", video_obj['id'])
         item.add_video_info("video_title", video_obj['vname'])
@@ -180,8 +181,8 @@ class ZhuWanWuFuSuRecommend(object):
         item.add_video_info("platform", self.platform)
         item.add_video_info("strategy", self.mode)
         item.add_video_info("session", "{}-{}".format(self.platform, int(time.time())))
-        item.add_video_info("user_id", self.user_dict['uid'])
-        item.add_video_info("user_name", self.user_dict['nick_name'])
+        item.add_video_info("user_id", our_user['uid'])
+        item.add_video_info("user_name", our_user['nick_name'])
         # 把扫描到的账号存到 accounts 表中
         self.manage_auth_id(out_user_id=video_obj['authid'], out_user_name=video_obj['authname'])
         mq_obj = item.produce_item()
@@ -262,11 +263,81 @@ class ZhuWanWuFuSuRecommend(object):
         else:
             return []
 
+    def get_detail_video_list(self):
+        url = "https://api.lidongze.cn/jeecg-boot/ugc/getDetailVideoListsEn2"
+        headers = {
+            'Host': 'api.lidongze.cn',
+            'xweb_xhr': '1',
+            'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36 MicroMessenger/6.8.0(0x16080000) NetType/WIFI MiniProgramEnv/Mac MacWechat/WMPF MacWechat/3.8.5(0x13080510)XWEB/1100',
+            'token': '',
+            'referer': 'https://servicewechat.com/wx0afdc2669ed8df2f/3/page-frame.html',
+            'accept-language': 'en-US,en;q=0.9'
+        }
+        page_index = 1
+        total_page = 2
+        while page_index <= total_page:
+            try:
+                if self.limit_flag:
+                    AliyunLogger.logging(
+                        code="2000",
+                        platform=self.platform,
+                        mode=self.mode,
+                        env=self.env,
+                        message="本轮已经抓取足够数量的视频"
+                    )
+                    return
+                query = {
+                    "groupId": "1650323161797439489",
+                    "pageNo": page_index,
+                    "pageSize": 10,
+                    # "videoId": "1681138763919003650",
+                    "appid": "wx0afdc2669ed8df2f",
+                    "type": 3,
+                    "hxid": "1556555457243828666"
+                }
+                params = {
+                    "v": self.cryptor.aes_encrypt(data=json.dumps(query))
+                }
+                response = requests.request("GET", url, headers=headers, params=params)
+                result = json.loads(self.cryptor.aes_decrypt(response.text))
+                total_page = result['list']['pages']
+                page_index = result['list']['current'] + 1
+                for index, video_obj in enumerate(result['list']['records'], 1):
+                    try:
+                        AliyunLogger.logging(
+                            code="1001",
+                            platform=self.platform,
+                            mode=self.mode,
+                            env=self.env,
+                            message="扫描到一条视频",
+                            data=video_obj
+                        )
+                        self.process_video_obj(video_obj)
+                    except Exception as e:
+                        AliyunLogger.logging(
+                            code="3000",
+                            platform=self.platform,
+                            mode=self.mode,
+                            env=self.env,
+                            message="抓取单条视频失败, 该视频位于第{}页第{}条报错原因是{}".format(page_index, index, e)
+                        )
+            except Exception as e:
+                AliyunLogger.logging(
+                    code="3000",
+                    platform=self.platform,
+                    mode=self.mode,
+                    env=self.env,
+                    message="抓取第{}页的时候失败, 报错原因是{}".format(page_index, e)
+                )
+            time.sleep(random.randint(5, 10))
+
     def schedule(self):
         """
-        先抓取推荐列表的视频， 等待 5 分钟后，抓取账号视频
+        先抓取推荐列表的视频， 等待 2 分钟后抓取 detail 页面，等待 5 分钟后，抓取账号视频
         """
         self.get_recommend_list()
+        time.sleep(2 * 60)
+        self.get_detail_video_list()
         time.sleep(5 * 60)
         self.mode = "author"
         user_list = self.get_user_list()
@@ -294,4 +365,4 @@ class ZhuWanWuFuSuRecommend(object):
 
 
 if __name__ == '__main__':
-    pass
+    pass

zhuwanwufusu/zhuwanwufusu_recommend/zwwfs_recommend_test.py

@@ -1,8 +1,5 @@
 import os
-import re
-import base64
 import json
-import random
 import sys
 import time
 import uuid
@@ -11,9 +8,9 @@ import requests
 
 sys.path.append(os.getcwd())
 from common.video_item import VideoItem
-from common import PiaoQuanPipeline, AliyunLogger, tunnel_proxies
+from common import tunnel_proxies
+from common.pipeline import PiaoQuanPipelineTest
 from common.mq import MQ
-from common.scheduling_db import MysqlHelper
 from zhuwanwufusu.crypt import AESCipher as AES
 
 
@@ -64,7 +61,6 @@ class ZhuWanWuFuSuRecommend(object):
                 self.process_video_obj(video_obj)
 
     def process_video_obj(self, video_obj):
-        print(json.dumps(video_obj, ensure_ascii=False, indent=4))
         trace_id = self.platform + str(uuid.uuid1())
         play_cnt = int(video_obj['playnum'].replace("万+", "0000")) if "万+" in video_obj['playnum'] else int(
             video_obj['playnum'])
@@ -85,7 +81,7 @@ class ZhuWanWuFuSuRecommend(object):
         item.add_video_info("user_name", self.user_dict['nick_name'])
 
         mq_obj = item.produce_item()
-        pipeline = PiaoQuanPipeline(
+        pipeline = PiaoQuanPipelineTest(
             platform=self.platform,
             mode=self.mode,
             rule_dict=self.rule_dict,
@@ -105,6 +101,6 @@ if __name__ == '__main__':
         mode="recommend",
         rule_dict={},
         user_dict={"uid": 123456, "nick_name": "luojunhuishuaige"},
-        env="dev"
+        env="prod"
     )
     Z.get_recommend_list()