调试

application/config/topic_group_queue.py

@@ -25,6 +25,7 @@ class TopicGroup(object):
             ('ttjfq', 'recommend', 'tiantianjufuqi'),
             ('zfkz', 'recommend', 'zhufukuaizhuan'),
             ('lpld', 'recommend', 'lepaoledong'),
+            ('lplddj', 'recommend', 'lepaoledongdijie'),
             ('pqgs', 'recommend', 'piaoquangushi'),
             ('wqsp', 'recommend', 'weiquanshipin'),
             ('llklzf', 'recommend', 'linglingkuailezhufu'),

application/pipeline/pipeline.py

@@ -129,7 +129,7 @@ class PiaoQuanPipeline(object):
         视频是否重复
         :return:
         """
-        if self.platform == "zhufuniannianshunxinjixiang" or  self.platform == "weiquanshipin" or  self.platform == "piaoquangushi" or  self.platform == "lepaoledong" or  self.platform == "zhufukuaizhuan" or self.platform == "linglingkuailezhufu":
+        if self.platform == "zhufuniannianshunxinjixiang" or  self.platform == "weiquanshipin" or  self.platform == "piaoquangushi" or  self.platform == "lepaoledong" or  self.platform == "zhufukuaizhuan" or self.platform == "linglingkuailezhufu" or self.platform == "lepaoledongdijie":
             return True
         if self.platform == "jierizhufuhuakaifugui" or self.platform == "yuannifuqimanman" or self.platform == "haoyunzhufuduo":
             return True

spider/ad_click/piaoquan_vlog.py

@@ -81,7 +81,7 @@ class PiaoQuanVlog(object):
             "extParams": '{"eventIds":"22040202,ab100,ab100,ab100,ab100,ab100,ab100,ab100,ab100,ab100,ab100","eventInfos":{"ab_test001":"ab100","ab_test002":"ab100","ab_test003":"ab100","ab_test004":"ab100","ab_test005":"ab100","ab_test006":"ab100","ab_test007":"ab100","ab_test008":"ab100","ab_test009":"ab100","ab_test010":"ab100"}}'
         }
         basic_response = requests.request("POST", self.url, headers=self.headers, data=payload,
-                                          proxies=tunnel_proxies()).json()
+                                          ).json()
         self.process_video_list(basic_response['data'])
 
     def process_video_list(self, video_list):

spider/crawler_author/xigua_author.py

@@ -102,7 +102,6 @@ class XiGuaAuthor(object):
                 url=url,
                 headers=headers,
                 params=params,
-                proxies=tunnel_proxies(),
                 timeout=5
             )
             off_set += 30

spider/crawler_online/dakaiyinghaoyun.py

@@ -123,7 +123,7 @@ class DKYHYRecommend(object):
                 "limit": 5,
                 "exp": {}
             })
-            response = requests.request("POST", url, headers=headers, data=payload, proxies=haiwai_tunnel_proxies())
+            response = requests.request("POST", url, headers=headers, data=payload)
             for index, video_obj in enumerate(response.json(), 1):
                 try:
                     self.aliyun_log.logging(

spider/crawler_online/lepaoledongdijie.py

@@ -0,0 +1,144 @@
+import os
+import random
+import sys
+import time
+import uuid
+import json
+
+
+import cv2
+import requests
+
+from application.common.mysql.sql import Sql
+from application.common.redis.xng_redis import xng_in_video_data
+
+sys.path.append(os.getcwd())
+
+from application.items import VideoItem
+from application.pipeline import PiaoQuanPipeline
+from application.common.messageQueue import MQ
+from application.common.log import AliyunLogger
+from application.common.mysql import MysqlHelper
+
+
+
+class LPLDDJRecommend(object):
+
+    """
+    乐跑乐动小程序推荐流-乐跑乐动迪捷
+    """
+
+    def __init__(self, platform, mode, rule_dict, user_list, env="prod"):
+        self.limit_flag = False
+        self.platform = platform
+        self.mode = mode
+        self.rule_dict = rule_dict
+        self.user_list = user_list
+        self.env = env
+        self.download_cnt = 0
+        self.mq = MQ(topic_name="topic_crawler_etl_" + self.env)
+        self.expire_flag = False
+        self.aliyun_log = AliyunLogger(mode=self.mode, platform=self.platform)
+        self.mysql = MysqlHelper(mode=self.mode, platform=self)
+
+
+    def get_recommend_list(self):
+        print("乐跑乐动迪捷")
+
+        """
+        获取推荐页视频
+        """
+        headers = {
+            'Content-Type': 'application/json'
+        }
+        url = "http://8.217.192.46:8889/crawler/le_pao_le_dong_di_jie/recommend"
+        # url = "http://8.217.192.46:8889/crawler/le_pao_le_dong/recommend"
+        while True:
+            payload = json.dumps({
+                "cursor": ""
+            })
+            response = requests.request("POST", url, headers=headers, data=payload)
+            response = response.json()
+            if response['code'] != 0:
+                self.aliyun_log.logging(
+                    code="3000",
+                    message="抓取单条视频失败,请求失败"
+                ),
+                return
+            data = response['data']['data']
+            if len(data) == 0:
+                return
+            for index, video_obj in enumerate(data, 1):
+                try:
+                    self.aliyun_log.logging(
+                        code="1001", message="扫描到一条视频", data=video_obj
+                    )
+                    self.process_video_obj(video_obj)
+                except Exception as e:
+                    self.aliyun_log.logging(
+                        code="3000",
+                        message="抓取单条视频失败, 该视频位于第{}页第{}条报错原因是{}".format(
+                            1, index, e
+                        ),
+                    )
+                if self.limit_flag:
+                    return
+                time.sleep(random.randint(1, 5))
+
+    def process_video_obj(self, video_obj):
+        """
+        处理视频
+        :param video_obj:
+        """
+        time.sleep(random.randint(3, 8))
+        trace_id = self.platform + str(uuid.uuid1())
+        our_user = random.choice(self.user_list)
+        item = VideoItem()
+        item.add_video_info("video_id", video_obj["uuid"])
+        item.add_video_info("video_title", video_obj["title"])
+        item.add_video_info("play_cnt", 0)
+        item.add_video_info("publish_time_stamp", int(time.time()))
+        item.add_video_info("out_user_id", video_obj["uuid"])
+        item.add_video_info("cover_url", video_obj["cover_url"])
+        item.add_video_info("like_cnt", 0)
+        item.add_video_info("share_cnt", 0)
+        item.add_video_info("comment_cnt", 0)
+        item.add_video_info("video_url", video_obj["urls"][0])
+        item.add_video_info("out_video_id", video_obj["uuid"])
+        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", our_user["uid"])
+        item.add_video_info("user_name", our_user["nick_name"])
+        mq_obj = item.produce_item()
+        pipeline = PiaoQuanPipeline(
+            platform=self.platform,
+            mode=self.mode,
+            rule_dict=self.rule_dict,
+            env=self.env,
+            item=mq_obj,
+            trace_id=trace_id,
+        )
+        if pipeline.process_item():
+            self.download_cnt += 1
+            self.mq.send_msg(mq_obj)
+            self.aliyun_log.logging(code="1002", message="成功发送至 ETL", data=mq_obj)
+            if self.download_cnt >= int(
+                    self.rule_dict.get("videos_cnt", {}).get("min", 200)
+            ):
+                self.limit_flag = True
+
+    def run(self):
+        self.get_recommend_list()
+
+
+if __name__ == '__main__':
+    J = LPLDDJRecommend(
+        platform="lepaoledongdijie",
+        mode="recommend",
+        rule_dict={},
+        user_list=[{'uid': "123456", 'nick_name': "xiaoxiao"}],
+
+    )
+    J.get_recommend_list()
+    # J.logic()

spider/spider_map.py

@@ -10,6 +10,7 @@ from spider.crawler_online.dakaiyinghaoyun import DKYHYRecommend
 from spider.crawler_online.haoyunzhufuduo import HYZFDfRecommend
 from spider.crawler_online.jierizhufuhuakaifugui import JRZFHKFGRecommend
 from spider.crawler_online.lepaoledong import LPLDRecommend
+from spider.crawler_online.lepaoledongdijie import LPLDDJRecommend
 from spider.crawler_online.linglingkuailezhufu import LlklzfRecommend
 from spider.crawler_online.piaoquangushi import PQGSRecommend
 from spider.crawler_online.weiquanshipin import WQSPRecommend
@@ -124,6 +125,10 @@ spider_map = {
     "haoyunzhufuduo": {
         "recommend": HYZFDfRecommend
     },
+    # 乐跑乐动迪捷
+    "lepaoledongdijie": {
+        "recommend": LPLDDJRecommend
+    },
     # 祝福年年顺心吉祥
     "zhufuniannianshunxinjixiang": {
         "recommend": ZFNNSXJXRecommend