123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584 |
- # -*- coding: utf-8 -*-
- # @Author: wangkun
- # @Time: 2023/3/15
- import datetime
- import json
- import os
- import random
- import shutil
- import sys
- import time
- from hashlib import md5
- import requests
- import urllib3
- from common.mq import MQ
- sys.path.append(os.getcwd())
- from common.common import Common
- from common.feishu import Feishu
- from common.publish import Publish
- from common.scheduling_db import MysqlHelper
- from common.public import get_config_from_mysql, download_rule
- proxies = {"http": None, "https": None}
- class XiaoniangaoHourScheduling:
- platform = "小年糕"
- words = "abcdefghijklmnopqrstuvwxyz0123456789"
- uid_token_dict = {
- "uid": f"""{"".join(random.sample(words, 8))}-{"".join(random.sample(words, 4))}-{"".join(random.sample(words, 4))}-{"".join(random.sample(words, 4))}-{"".join(random.sample(words, 12))}""",
- "token": "".join(random.sample(words, 32))
- }
- @classmethod
- def repeat_video(cls, log_type, crawler, video_id, env):
- # sql = f""" select * from crawler_video where platform="小年糕" and out_video_id="{video_id}"; """
- sql = f""" select * from crawler_video where platform in ("{crawler}","{cls.platform}") and out_video_id="{video_id}"; """
- repeat_video = MysqlHelper.get_values(log_type, crawler, sql, env)
- return len(repeat_video)
- @classmethod
- def repeat_hour(cls, log_type, crawler, video_id, env):
- sql = f""" select * from crawler_xiaoniangao_hour where platform="小年糕" and out_video_id="{video_id}"; """
- repeat_video = MysqlHelper.get_values(log_type, crawler, sql, env)
- return len(repeat_video)
- # 获取列表
- @classmethod
- def get_videoList(cls, log_type, crawler, rule_dict, env):
- uid_token_dict = cls.uid_token_dict
- url = "https://kapi-xng-app.xiaoniangao.cn/v2/trends/recommend"
- payload = "{\"topic_name\":\"recommend\",\"ext\":{\"current_item\":0,\"items\":[]},\"tag_id\":0,\"refresh\":false,\"share_width\":300,\"share_height\":240,\"staggered_style\":0,\"qs\":\"imageMogr2\\/gravity\\/center\\/rotate\\/$\\/thumbnail\\/!750x500r\\/interlace\\/1\\/format\\/jpg\",\"topic_id\":2,\"h_qs\":\"imageMogr2\\/gravity\\/center\\/rotate\\/$\\/thumbnail\\/!80x80r\\/interlace\\/1\\/format\\/jpg\",\"log\":{\"net\":\"wifi\",\"product\":\"xng\",\"uid\":\"2F310D09-5E32-5985-8644-3BCB6920E76F\",\"brand\":\"iPad\",\"page\":\"\",\"session_id\":\"71C77648-3224-4083-894C-B6282131F286\",\"resolution\":\"750*1334\",\"pf\":\"4\",\"app_version\":\"1.22.5\",\"device\":\"iPad Pro (12.9-inch) (3rd generation)\",\"os_version\":\"15.7\",\"idfa\":\"\",\"channel\":\"ios_app_store\"},\"token\":\"\"}"
- headers = {
- 'Host': 'kapi-xng-app.xiaoniangao.cn',
- 'content-type': 'application/json; charset=utf-8',
- 'accept': 'application/json',
- 'authorization': 'PsrUTBCQ5G7UVZdgx+JxymPHcKU=',
- 'verb': 'POST',
- 'content-md5': '08fa0e6bf725fd6ef83c16d2ceb8a544',
- 'x-b3-traceid': '45a6c5b4c471eecc',
- 'accept-language': 'zh-Hans-CN;q=1.0',
- 'date': 'Mon, 19 Jun 2023 09:47:40 GMT',
- 'x-token-id': '',
- 'x-signaturemethod': 'hmac-sha1',
- 'user-agent': 'xngapp/1.22.5 (cn.xiaoniangao.xngapp; build:157; iOS 15.7.0) Alamofire/5.2.2'
- }
- urllib3.disable_warnings()
- r = requests.post(url=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).warning(f"get_videoList:{r.json()}\n")
- Common.logging(log_type, crawler, env, f"get_videoList:{r.json()}\n")
- return
- elif "list" not in r.json()["data"]:
- 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
- elif len(r.json()['data']['list']) == 0:
- Common.logger(log_type, crawler).warning(f"get_videoList:{r.json()['data']['list']}\n")
- Common.logging(log_type, crawler, env, f"get_videoList:{r.json()['data']['list']}\n")
- return
- else:
- # 视频列表数据
- feeds = r.json()["data"]["list"]
- for i in range(len(feeds)):
- try:
- # 标题,表情随机加在片头、片尾,或替代句子中间的标点符号
- xiaoniangao_title = feeds[i].get("title", "").strip().replace("\n", "") \
- .replace("/", "").replace("\r", "").replace("#", "") \
- .replace(".", "。").replace("\\", "").replace("&NBSP", "") \
- .replace(":", "").replace("*", "").replace("?", "") \
- .replace("?", "").replace('"', "").replace("<", "") \
- .replace(">", "").replace("|", "").replace(" ", "")\
- .replace('"', '').replace("'", '')
- # 随机取一个表情/符号
- emoji = random.choice(get_config_from_mysql(log_type, crawler, env, "emoji"))
- # 生成最终标题,标题list[表情+title, title+表情]随机取一个
- video_title = random.choice([f"{emoji}{xiaoniangao_title}", f"{xiaoniangao_title}{emoji}"])
- # 发布时间
- publish_time_stamp = int(int(feeds[i].get("t", 0))/1000)
- publish_time_str = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(publish_time_stamp))
- # 用户名 / 头像
- user_name = feeds[i].get("user", {}).get("nick", "").strip().replace("\n", "") \
- .replace("/", "").replace(" ", "") \
- .replace(" ", "").replace("&NBSP", "").replace("\r", "")
- video_dict = {
- "video_title": video_title,
- "video_id": feeds[i].get("vid", ""),
- "duration": int(feeds[i].get("du", 0)/1000),
- "play_cnt": feeds[i].get("play_pv", 0),
- "like_cnt": feeds[i].get("favor", {}).get("total", 0),
- "comment_cnt": feeds[i].get("comment_count", 0),
- "share_cnt": feeds[i].get("share", 0),
- "user_name": user_name,
- "publish_time_stamp": publish_time_stamp,
- "publish_time_str": publish_time_str,
- "video_width": int(feeds[i].get("vw", 0)),
- "video_height": int(feeds[i].get("vh", 0)),
- "avatar_url": feeds[i].get("user", {}).get("hurl", ""),
- "profile_id": feeds[i]["id"],
- "profile_mid": feeds[i]["user"]["mid"],
- "cover_url": feeds[i].get("url", ""),
- "video_url": feeds[i].get("v_url", ""),
- "session": f"xiaoniangao-hour-{int(time.time())}"
- }
- 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}")
- # 过滤无效视频
- if video_title == "" or video_dict["video_id"] == "" or video_dict["video_url"] == "":
- Common.logger(log_type, crawler).warning("无效视频\n")
- Common.logging(log_type, crawler, env, "无效视频\n")
- # 抓取基础规则过滤
- 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:
- # 写入飞书小时级feeds数据库表
- insert_sql = f""" insert into crawler_xiaoniangao_hour(profile_id,
- profile_mid,
- platform,
- out_video_id,
- video_title,
- user_name,
- cover_url,
- video_url,
- duration,
- publish_time,
- play_cnt,
- crawler_time_stamp,
- crawler_time)
- values({video_dict["profile_id"]},
- {video_dict["profile_mid"]},
- "{cls.platform}",
- "{video_dict["video_id"]}",
- "{video_title}",
- "{user_name}",
- "{video_dict["cover_url"]}",
- "{video_dict["video_url"]}",
- {video_dict["duration"]},
- "{publish_time_str}",
- {video_dict["play_cnt"]},
- {int(time.time())},
- "{time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(int(time.time())))}"
- )"""
- Common.logger(log_type, crawler).info(f"insert_sql:{insert_sql}")
- Common.logging(log_type, crawler, env, f"insert_sql:{insert_sql}")
- MysqlHelper.update_values(log_type, crawler, insert_sql, env)
- Common.logger(log_type, crawler).info('视频信息写入小时级数据库成功!\n')
- Common.logging(log_type, crawler, env, '视频信息写入小时级数据库成功!\n')
- 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")
- @classmethod
- def get_video_info(cls, log_type, crawler, p_id, p_mid, v_title, v_id):
- uid_token_dict = cls.uid_token_dict
- url = "https://kapi.xiaoniangao.cn/profile/get_profile_by_id"
- headers = {
- "x-b3-traceid": '1c403a4aa72e3c',
- "X-Token-Id": 'ab619e96d801f1567388629260aa68ec-1202200806',
- "uid": uid_token_dict['uid'],
- "content-type": "application/json",
- "Accept-Encoding": "gzip,compress,br,deflate",
- "User-Agent": 'Mozilla/5.0 (iPhone; CPU iPhone OS 14_7_1 like Mac OS X)'
- ' AppleWebKit/605.1.15 (KHTML, like Gecko) Mobile/15E148 '
- 'MicroMessenger/8.0.20(0x18001432) NetType/WIFI Language/zh_CN',
- "Referer": 'https://servicewechat.com/wxd7911e4c177690e4/624/page-frame.html'
- }
- data = {
- "play_src": "1",
- "profile_id": int(p_id),
- "profile_mid": int(p_mid),
- "qs": "imageMogr2/gravity/center/rotate/$/thumbnail/"
- "!400x400r/crop/400x400/interlace/1/format/jpg",
- "h_qs": "imageMogr2/gravity/center/rotate/$/thumbnail"
- "/!80x80r/crop/80x80/interlace/1/format/jpg",
- "share_width": 625,
- "share_height": 500,
- "no_comments": True,
- "no_follow": True,
- "vid": v_id,
- "hot_l1_comment": True,
- "token": uid_token_dict['token'],
- "uid": uid_token_dict['uid'],
- "proj": "ma",
- "wx_ver": "8.0.20",
- "code_ver": "3.62.0",
- "log_common_params": {
- "e": [{
- "data": {
- "page": "dynamicSharePage"
- }
- }],
- "ext": {
- "brand": "iPhone",
- "device": "iPhone 11",
- "os": "iOS 14.7.1",
- "weixinver": "8.0.20",
- "srcver": "2.24.3",
- "net": "wifi",
- "scene": "1089"
- },
- "pj": "1",
- "pf": "2",
- "session_id": "7bcce313-b57d-4305-8d14-6ebd9a1bad29"
- }
- }
- urllib3.disable_warnings()
- r = requests.post(headers=headers, url=url, json=data, proxies=proxies, verify=False)
- if r.status_code != 200 or 'data' not in r.text:
- Common.logger(log_type, crawler).warning(f"get_videoInfo:{r.text}\n")
- else:
- hour_play_cnt = r.json()["data"]["play_pv"]
- hour_cover_url = r.json()["data"]["url"]
- hour_video_url = r.json()["data"]["v_url"]
- hour_video_duration = r.json()["data"]["du"]
- hour_video_comment_cnt = r.json()["data"]["comment_count"]
- hour_video_like_cnt = r.json()["data"]["favor"]["total"]
- hour_video_share_cnt = r.json()["data"]["share"]
- hour_video_width = r.json()["data"]["w"]
- hour_video_height = r.json()["data"]["h"]
- hour_video_send_time = r.json()["data"]["t"]
- publish_time_stamp = int(int(hour_video_send_time) / 1000)
- publish_time_str = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(publish_time_stamp))
- hour_user_name = r.json()["data"]["user"]["nick"]
- hour_head_url = r.json()["data"]["user"]["hurl"]
- video_info_dict = {
- "video_id": v_id,
- "video_title": v_title,
- "duration": hour_video_duration,
- "play_cnt": hour_play_cnt,
- "like_cnt": hour_video_like_cnt,
- "comment_cnt": hour_video_comment_cnt,
- "share_cnt": hour_video_share_cnt,
- "user_name": hour_user_name,
- "publish_time_stamp": publish_time_stamp,
- "publish_time_str": publish_time_str,
- "video_width": hour_video_width,
- "video_height": hour_video_height,
- "avatar_url": hour_head_url,
- "profile_id": p_id,
- "profile_mid": p_mid,
- "cover_url": hour_cover_url,
- "video_url": hour_video_url,
- "session": f"xiaoniangao-hour-{int(time.time())}"
- }
- return video_info_dict
- # 更新小时榜数据
- @classmethod
- def update_videoList(cls, log_type, crawler, rule_dict, our_uid, env):
- """
- 更新小时榜数据
- """
- befor_yesterday = (datetime.date.today() + datetime.timedelta(days=-3)).strftime("%Y-%m-%d %H:%M:%S")
- update_time_stamp = int(time.mktime(time.strptime(befor_yesterday, "%Y-%m-%d %H:%M:%S")))
- select_sql = f""" select * from crawler_xiaoniangao_hour where crawler_time_stamp>={update_time_stamp} GROUP BY out_video_id DESC """
- update_video_list = MysqlHelper.get_values(log_type, crawler, select_sql, env)
- if len(update_video_list) == 0:
- Common.logger(log_type, crawler).info("暂无需要更新的小时榜数据\n")
- Common.logging(log_type, crawler, env, "暂无需要更新的小时榜数据\n")
- return
- for update_video_info in update_video_list:
- try:
- profile_id = update_video_info["profile_id"]
- profile_mid = update_video_info["profile_mid"]
- video_title = update_video_info["video_title"]
- video_id = update_video_info["out_video_id"]
- if datetime.datetime.now().hour == 10 and datetime.datetime.now().minute <= 10:
- video_info_dict = cls.get_video_info(log_type=log_type,
- crawler=crawler,
- p_id=profile_id,
- p_mid=profile_mid,
- v_title=video_title,
- v_id=video_id)
- ten_play_cnt = video_info_dict['play_cnt']
- Common.logger(log_type, crawler).info(f"ten_play_cnt:{ten_play_cnt}")
- Common.logging(log_type, crawler, env, f"ten_play_cnt:{ten_play_cnt}")
- update_sql = f""" update crawler_xiaoniangao_hour set ten_play_cnt={ten_play_cnt} WHERE out_video_id="{video_id}"; """
- # Common.logger(log_type, crawler).info(f"update_sql:{update_sql}")
- MysqlHelper.update_values(log_type, crawler, update_sql, env)
- cls.download_publish(log_type=log_type,
- crawler=crawler,
- video_info_dict=video_info_dict,
- rule_dict=rule_dict,
- update_video_info=update_video_info,
- our_uid=our_uid,
- env=env)
- elif datetime.datetime.now().hour == 15 and datetime.datetime.now().minute <= 10:
- video_info_dict = cls.get_video_info(log_type=log_type,
- crawler=crawler,
- p_id=profile_id,
- p_mid=profile_mid,
- v_title=video_title,
- v_id=video_id)
- fifteen_play_cnt = video_info_dict['play_cnt']
- Common.logger(log_type, crawler).info(f"fifteen_play_cnt:{fifteen_play_cnt}")
- Common.logging(log_type, crawler, env, f"fifteen_play_cnt:{fifteen_play_cnt}")
- update_sql = f""" update crawler_xiaoniangao_hour set fifteen_play_cnt={fifteen_play_cnt} WHERE out_video_id="{video_id}"; """
- # Common.logger(log_type, crawler).info(f"update_sql:{update_sql}")
- MysqlHelper.update_values(log_type, crawler, update_sql, env)
- cls.download_publish(log_type=log_type,
- crawler=crawler,
- video_info_dict=video_info_dict,
- rule_dict=rule_dict,
- update_video_info=update_video_info,
- our_uid=our_uid,
- env=env)
- elif datetime.datetime.now().hour == 20 and datetime.datetime.now().minute <= 10:
- video_info_dict = cls.get_video_info(log_type=log_type,
- crawler=crawler,
- p_id=profile_id,
- p_mid=profile_mid,
- v_title=video_title,
- v_id=video_id)
- twenty_play_cnt = video_info_dict['play_cnt']
- Common.logger(log_type, crawler).info(f"twenty_play_cnt:{twenty_play_cnt}")
- Common.logging(log_type, crawler, env, f"twenty_play_cnt:{twenty_play_cnt}")
- update_sql = f""" update crawler_xiaoniangao_hour set twenty_play_cnt={twenty_play_cnt} WHERE out_video_id="{video_id}"; """
- # Common.logger(log_type, crawler).info(f"update_sql:{update_sql}")
- MysqlHelper.update_values(log_type, crawler, update_sql, env)
- cls.download_publish(log_type=log_type,
- crawler=crawler,
- video_info_dict=video_info_dict,
- rule_dict=rule_dict,
- update_video_info=update_video_info,
- our_uid=our_uid,
- env=env)
- else:
- pass
- except Exception as e:
- Common.logger(log_type, crawler).error(f'更新{update_video_info["video_title"]}时异常:{e}\n')
- Common.logging(log_type, crawler, env, f'更新{update_video_info["video_title"]}时异常:{e}\n')
- @classmethod
- def send_to_mq(cls, log_type, crawler, video_info_dict, rule_dict, env):
- video_info_dict["out_user_id"] = video_info_dict["profile_id"]
- video_info_dict["platform"] = crawler
- video_info_dict["strategy"] = log_type
- video_info_dict["out_video_id"] = video_info_dict["video_id"]
- video_info_dict["width"] = video_info_dict["video_width"]
- video_info_dict["height"] = video_info_dict["video_height"]
- video_info_dict["crawler_rule"] = json.dumps(rule_dict)
- video_info_dict["user_id"] = video_info_dict["uid"]
- video_info_dict["publish_time"] = video_info_dict["publish_time_str"]
- video_info_dict["strategy_type"] = "hour"
- mq = MQ(topic_name="topic_crawler_etl_" + env)
- mq.send_msg(video_info_dict)
- @classmethod
- def download(cls, log_type, crawler, video_info_dict, rule_dict, our_uid, env):
- # 下载视频
- Common.download_method(log_type=log_type, crawler=crawler, text="video", title=video_info_dict["video_title"],
- url=video_info_dict["video_url"])
- md_title = md5(video_info_dict['video_title'].encode('utf8')).hexdigest()
- try:
- if os.path.getsize(f"./{crawler}/videos/{md_title}/video.mp4") == 0:
- # 删除视频文件夹
- shutil.rmtree(f"./{crawler}/videos/{md_title}")
- Common.logger(log_type, crawler).info("视频size=0,删除成功\n")
- Common.logging(log_type, crawler, env, "视频size=0,删除成功\n")
- return
- except FileNotFoundError:
- # 删除视频文件夹
- shutil.rmtree(f"./{crawler}/videos/{md_title}")
- Common.logger(log_type, crawler).info("视频文件不存在,删除文件夹成功\n")
- Common.logging(log_type, crawler, env, "视频文件不存在,删除文件夹成功\n")
- return
- # 下载封面
- Common.download_method(log_type=log_type, crawler=crawler, text="cover", title=video_info_dict["video_title"],
- url=video_info_dict["cover_url"])
- # 保存视频信息至 "./videos/{download_video_title}/info.txt"
- Common.save_video_info(log_type=log_type, crawler=crawler, video_dict=video_info_dict)
- # 上传视频
- Common.logger(log_type, crawler).info("开始上传视频...")
- Common.logging(log_type, crawler, env, "开始上传视频...")
- if env == "dev":
- oss_endpoint = "out"
- our_video_id = Publish.upload_and_publish(log_type=log_type,
- crawler=crawler,
- strategy="上升榜抓取策略",
- our_uid=our_uid,
- env=env,
- oss_endpoint=oss_endpoint)
- our_video_link = f"https://testadmin.piaoquantv.com/cms/post-detail/{our_video_id}/info"
- else:
- oss_endpoint = "inner"
- our_video_id = Publish.upload_and_publish(log_type=log_type,
- crawler=crawler,
- strategy="上升榜抓取策略",
- our_uid=our_uid,
- env=env,
- oss_endpoint=oss_endpoint)
- our_video_link = f"https://admin.piaoquantv.com/cms/post-detail/{our_video_id}/info"
- if our_video_id is None:
- try:
- # 删除视频文件夹
- shutil.rmtree(f"./{crawler}/videos/{md_title}")
- return
- except FileNotFoundError:
- return
- insert_sql = f""" insert into crawler_video(video_id,
- out_user_id,
- platform,
- strategy,
- out_video_id,
- video_title,
- cover_url,
- video_url,
- duration,
- publish_time,
- play_cnt,
- crawler_rule,
- width,
- height)
- values({our_video_id},
- "{video_info_dict['profile_id']}",
- "{cls.platform}",
- "上升榜抓取策略",
- "{video_info_dict['video_id']}",
- "{video_info_dict['video_title']}",
- "{video_info_dict['cover_url']}",
- "{video_info_dict['video_url']}",
- {int(video_info_dict['duration'])},
- "{video_info_dict['publish_time_str']}",
- {int(video_info_dict['play_cnt'])},
- '{json.dumps(rule_dict)}',
- {int(video_info_dict['video_width'])},
- {int(video_info_dict['video_height'])}) """
- Common.logger(log_type, crawler).info(f"insert_sql:{insert_sql}")
- Common.logging(log_type, crawler, env, f"insert_sql:{insert_sql}")
- MysqlHelper.update_values(log_type, crawler, insert_sql, env)
- Common.logger(log_type, crawler).info('视频信息插入数据库成功!')
- Common.logging(log_type, crawler, env, '视频信息插入数据库成功!')
- # 视频写入飞书
- Feishu.insert_columns(log_type, crawler, "yatRv2", "ROWS", 1, 2)
- # 视频ID工作表,首行写入数据
- upload_time = int(time.time())
- values = [[time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(upload_time)),
- "上升榜抓取策略",
- str(video_info_dict['video_id']),
- str(video_info_dict['video_title']),
- our_video_link,
- video_info_dict['play_cnt'],
- video_info_dict['comment_cnt'],
- video_info_dict['like_cnt'],
- video_info_dict['share_cnt'],
- video_info_dict['duration'],
- f"{video_info_dict['video_width']}*{video_info_dict['video_height']}",
- str(video_info_dict['publish_time_str'].replace("-", "/")),
- str(video_info_dict['user_name']),
- str(video_info_dict['profile_id']),
- str(video_info_dict['profile_mid']),
- str(video_info_dict['avatar_url']),
- str(video_info_dict['cover_url']),
- str(video_info_dict['video_url'])]]
- time.sleep(1)
- Feishu.update_values(log_type, crawler, "yatRv2", "F2:Z2", values)
- Common.logger(log_type, crawler).info('视频信息写入飞书成功\n')
- Common.logging(log_type, crawler, env, '视频信息写入飞书成功\n')
- # 下载/上传
- @classmethod
- def download_publish(cls, log_type, crawler, video_info_dict, rule_dict, update_video_info, our_uid, env):
- if cls.repeat_video(log_type, crawler, video_info_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')
- # 播放量大于 50000,直接下载
- elif int(video_info_dict["play_cnt"]) >= 30000:
- Common.logger(log_type, crawler).info(f"播放量:{video_info_dict['play_cnt']} >= 30000,满足下载规则,开始下载视频")
- Common.logging(log_type, crawler, env, f"播放量:{video_info_dict['play_cnt']} >= 30000,满足下载规则,开始下载视频")
- # cls.download(log_type=log_type,
- # crawler=crawler,
- # video_info_dict=video_info_dict,
- # rule_dict=rule_dict,
- # our_uid=our_uid,
- # env=env)
- cls.send_to_mq(log_type=log_type, crawler=crawler, video_info_dict=video_info_dict, rule_dict=rule_dict, env=env)
- # 上升榜判断逻辑,任意时间段上升量>=5000,连续两个时间段上升量>=2000
- elif int(update_video_info['ten_play_cnt']) >= 3000 or int(
- update_video_info['fifteen_play_cnt']) >= 3000 or int(update_video_info['twenty_play_cnt']) >= 3000:
- Common.logger(log_type, crawler).info(f"10:00 or 15:00 or 20:00 数据上升量:{int(update_video_info['ten_play_cnt'])} or {int(update_video_info['fifteen_play_cnt'])} or {int(update_video_info['twenty_play_cnt'])} >= 3000")
- Common.logging(log_type, crawler, env, f"10:00 or 15:00 or 20:00 数据上升量:{int(update_video_info['ten_play_cnt'])} or {int(update_video_info['fifteen_play_cnt'])} or {int(update_video_info['twenty_play_cnt'])} >= 3000")
- Common.logger(log_type, crawler).info("满足下载规则,开始下载视频")
- Common.logging(log_type, crawler, env, "满足下载规则,开始下载视频")
- # cls.download(log_type=log_type,
- # crawler=crawler,
- # video_info_dict=video_info_dict,
- # rule_dict=rule_dict,
- # our_uid=our_uid,
- # env=env)
- cls.send_to_mq(log_type=log_type, crawler=crawler, video_info_dict=video_info_dict, rule_dict=rule_dict, env=env)
- elif int(update_video_info['ten_play_cnt']) >= 1000 and int(update_video_info['fifteen_play_cnt']) >= 1000:
- Common.logger(log_type, crawler).info(f"10:00 and 15:00 数据上升量:{int(update_video_info['ten_play_cnt'])} and {int(update_video_info['fifteen_play_cnt'])} >= 1000")
- Common.logging(log_type, crawler, env, f"10:00 and 15:00 数据上升量:{int(update_video_info['ten_play_cnt'])} and {int(update_video_info['fifteen_play_cnt'])} >= 1000")
- Common.logger(log_type, crawler).info("满足下载规则,开始下载视频")
- Common.logging(log_type, crawler, env, "满足下载规则,开始下载视频")
- # cls.download(log_type=log_type,
- # crawler=crawler,
- # video_info_dict=video_info_dict,
- # rule_dict=rule_dict,
- # our_uid=our_uid,
- # env=env)
- cls.send_to_mq(log_type=log_type, crawler=crawler, video_info_dict=video_info_dict, rule_dict=rule_dict, env=env)
- elif int(update_video_info['fifteen_play_cnt']) >= 1000 and int(update_video_info['twenty_play_cnt']) >= 1000:
- Common.logger(log_type, crawler).info(
- f"15:00 and 20:00 数据上升量:{int(update_video_info['fifteen_play_cnt'])} and {int(update_video_info['twenty_play_cnt'])} >= 1000")
- Common.logging(log_type, crawler, env, f"15:00 and 20:00 数据上升量:{int(update_video_info['fifteen_play_cnt'])} and {int(update_video_info['twenty_play_cnt'])} >= 1000")
- Common.logger(log_type, crawler).info("满足下载规则,开始下载视频")
- Common.logging(log_type, crawler, env, "满足下载规则,开始下载视频")
- # cls.download(log_type=log_type,
- # crawler=crawler,
- # video_info_dict=video_info_dict,
- # rule_dict=rule_dict,
- # our_uid=our_uid,
- # env=env)
- cls.send_to_mq(log_type=log_type, crawler=crawler, video_info_dict=video_info_dict, rule_dict=rule_dict, env=env)
- elif int(update_video_info['ten_play_cnt']) >= 1000 and int(update_video_info['twenty_play_cnt']) >= 1000:
- Common.logger(log_type, crawler).info(
- f"今日10:00 / 20:00数据上升量:{int(update_video_info['ten_play_cnt'])} and {int(update_video_info['twenty_play_cnt'])} >= 1000")
- Common.logging(log_type, crawler, env, f"今日10:00 / 20:00数据上升量:{int(update_video_info['ten_play_cnt'])} and {int(update_video_info['twenty_play_cnt'])} >= 1000")
- Common.logger(log_type, crawler).info("满足下载规则,开始下载视频")
- Common.logging(log_type, crawler, env, "满足下载规则,开始下载视频")
- # cls.download(log_type=log_type,
- # crawler=crawler,
- # video_info_dict=video_info_dict,
- # rule_dict=rule_dict,
- # our_uid=our_uid,
- # env=env)
- cls.send_to_mq(log_type=log_type, crawler=crawler, video_info_dict=video_info_dict, rule_dict=rule_dict, env=env)
- else:
- Common.logger(log_type, crawler).info("上升量不满足下载规则")
- Common.logging(log_type, crawler, env, "上升量不满足下载规则")
- if __name__ == "__main__":
- print(get_config_from_mysql(log_type='hour', source='xiaoniangao', env='dev', text='filter'))
- pass
|