import json import random import time import uuid import requests from common.common import Common from common.scheduling_db import MysqlHelper from common.mq import MQ from common.public import download_rule, get_config_from_mysql proxies = {"http": None, "https": None} headers = { 'Host': 'kkj.xinhuachuanmeijs.com', 'content-type': 'application/x-www-form-urlencoded', 'accept-language': 'zh-cn', 'user-agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Mobile/15E217 MicroMessenger/6.8.0(0x16080000) NetType/WIFI Language/en Branch/Br_trunk MiniProgramEnv/Mac', 'referer': 'https://servicewechat.com/wxdba4e6f4302f4343/6/page-frame.html', # 'Cookie': 'PHPSESSID=dd259803ffecb8e91b75b376241c3fe6' } class LndwzfRecommend: platform = ("老年队伍-祝福") download_cnt = 0 element_list = [] i = 0 @classmethod def get_video_url(cls, vid, log_type, crawler, env): try: url = "https://kkj.xinhuachuanmeijs.com/app/index.php?i=329&t=0&m=jyt_txvideo&v=1.0&from=wxapp&c=entry&a=wxapp&do=videoinfo&vid={}&version=1.0.3".format(vid) payload={} r = requests.request("GET", url, headers=headers, data=payload, proxies=proxies, verify=False) if "data" not in r.text or r.status_code != 200: Common.logger(log_type, crawler).warning(f"get_videoList:{r.text}\n") Common.logging(log_type, crawler, env, f"get_videoList:{r.text}\n") return elif "data" not in r.json(): Common.logger(log_type, crawler).info(f"get_videoList:{r.json()}\n") Common.logging(log_type, crawler, env, f"get_videoList:{r.json()}\n") return elif len(r.json()["data"]) == 0: Common.logger(log_type, crawler).warning(f"get_videoList:{r.json()['data']}\n") Common.logging(log_type, crawler, env, f"get_videoList:{r.json()['data']}\n") return else: # 获取视频url data = r.json()["data"] return data except Exception as e: Common.logger(log_type, crawler).error(f" 获取视频链接异常:{e}\n") Common.logging(log_type, crawler, env, f"获取视频链接异常:{e}\n") @classmethod def repeat_video(cls, log_type, crawler, video_id, env): sql = f""" select * from crawler_video where platform in ("{crawler}","{cls.platform}") and create_time>='2023-06-26' and out_video_id="{video_id}"; """ repeat_video = MysqlHelper.get_values(log_type, crawler, sql, env) return len(repeat_video) @classmethod def get_vlist(cls, page, log_type, crawler, env): url = "https://kkj.xinhuachuanmeijs.com/app/index.php?i=329&t=0&m=jyt_txvideo&v=1.0&from=wxapp&c=entry&a=wxapp&do=videolist" payload = f"category=3600&page={page}&israndom=1&type=4&noauth=true" r = requests.request("POST", url, headers=headers, data=payload, proxies=proxies, verify=False) if "data" not in r.text or r.status_code != 200: Common.logger(log_type, crawler).warning(f"get_videoList:{r.text}\n") Common.logging(log_type, crawler, env, f"get_videoList:{r.text}\n") return elif "data" not in r.json(): Common.logger(log_type, crawler).info(f"get_videoList:{r.json()}\n") Common.logging(log_type, crawler, env, f"get_videoList:{r.json()}\n") return elif len(r.json()["data"]) == 0: Common.logger(log_type, crawler).warning(f"get_videoList:{r.json()['data']}\n") Common.logging(log_type, crawler, env, f"get_videoList:{r.json()['data']}\n") return else: return r @classmethod def get_videoList(cls, log_type, crawler, our_uid, rule_dict, env): mq = MQ(topic_name="topic_crawler_etl_" + env) uuid1 = str(uuid.uuid1()) for page in range(1, 101): try: Common.logger(log_type, crawler).info(f"正在抓取第{page}页") Common.logging(log_type, crawler, env, f"正在抓取第{page}页") # 获取列表 list = cls.get_vlist(page, log_type, crawler, env) # 视频列表 feeds = list.json()["data"] for i in range(len(feeds)): try: if cls.download_cnt >= int(rule_dict.get("videos_cnt", {}).get("min", 10)): cls.i = 0 cls.download_cnt = 0 cls.element_list = [] return cls.i += 1 video_title = feeds[i].get("vtitle", "").strip().replace("\n", "") \ .replace("/", "").replace("\\", "").replace("\r", "") \ .replace(":", "").replace("*", "").replace("？", "") \ .replace("?", "").replace('"', "").replace("<", "") \ .replace(">", "").replace("|", "").replace(" ", "") \ .replace("&NBSP", "").replace(".", "。").replace(" ", "") \ .replace("'", "").replace("#", "").replace("Merge", "") publish_time_stamp = int(time.time()) publish_time_str = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(publish_time_stamp)) vid = feeds[i]["vid"] # 获取视频链接 video_page = cls.get_video_url(vid, log_type, crawler, env) video_dict = { "video_title": video_title, "video_id": feeds[i]["vid"], # 视频id "publish_time_stamp": publish_time_stamp, "publish_time_str": publish_time_str, "is_video": int(feeds[i].get("is_video", 0)), # 类型 "category_id": int(feeds[i].get("category_id", 0)), # 视频来源 "cover_url": video_page.get("cover", ""), # 视频封面 "video_url": video_page.get("res"), # 视频链接 "click": int(feeds[i].get("click", 0)), # 点击数 "video_time": int(feeds[i].get("vtime", 0)), # 视频时长（m） "video_width": int(feeds[i].get("vw", 0)), "video_height": int(feeds[i].get("vh", 0)), "user_name": feeds[i].get("source", "").strip().replace("\n", ""), "user_id": feeds[i].get("openid", ""), "play_cnt": 0, "like_cnt": 0, "comment_cnt": 0, "share_cnt": 0, # "duration": feeds[i].get("mediaDuration", 0), "session": "" } for k, v in video_dict.items(): Common.logger(log_type, crawler).info(f"{k}:{v}") Common.logging(log_type, crawler, env, f"video_dict:{video_dict}") if video_dict["video_id"] == "" or video_dict["video_title"] == "" or video_dict[ "video_url"] == "": Common.logger(log_type, crawler).info("无效视频\n") Common.logging(log_type, crawler, env, "无效视频\n") elif download_rule(log_type=log_type, crawler=crawler, video_dict=video_dict, rule_dict=rule_dict) is False: Common.logger(log_type, crawler).info("不满足抓取规则\n") Common.logging(log_type, crawler, 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=log_type, source=crawler, env=env, text="filter", action="")) is True: Common.logger(log_type, crawler).info('已中过滤词\n') Common.logging(log_type, crawler, env, '已中过滤词\n') elif cls.repeat_video(log_type, crawler, video_dict["video_id"], env) != 0: Common.logger(log_type, crawler).info('视频已下载\n') Common.logging(log_type, crawler, env, '视频已下载\n') else: video_dict["out_user_id"] = video_dict["user_id"] video_dict["platform"] = crawler video_dict["strategy"] = log_type video_dict["out_video_id"] = video_dict["video_id"] video_dict["width"] = video_dict["video_width"] video_dict["height"] = video_dict["video_height"] video_dict["crawler_rule"] = json.dumps(rule_dict) video_dict["user_id"] = our_uid video_dict["publish_time"] = video_dict["publish_time_str"] mq.send_msg(video_dict) cls.download_cnt += 1 interval = random.randrange(5, 11) time.sleep(interval) except Exception as e: Common.logger(log_type, crawler).error(f"抓取单条视频异常:{e}\n") Common.logging(log_type, crawler, env, f"抓取单条视频异常:{e}\n") except Exception as e: Common.logger(log_type, crawler).error(f"抓取第{page}页时异常:{e}\n") Common.logging(log_type, crawler, env, f"抓取第{page}页时异常:{e}\n") if __name__ == "__main__": rule_dict1 = {"period": {"min": 365, "max": 365}, "duration": {"min": 30, "max": 1800}, "favorite_cnt": {"min": 0, "max": 0}, "videos_cnt": {"min": 10, "max": 20}, "share_cnt": {"min": 0, "max": 0}} LndwzfRecommend.get_videoList("recommend", "laonianduiwu,", "16QspO", rule_dict1, 'dev')