|
@@ -4,6 +4,7 @@
|
|
|
import datetime
|
|
|
import json
|
|
|
import os
|
|
|
+import random
|
|
|
import shutil
|
|
|
import sys
|
|
|
import time
|
|
@@ -322,12 +323,6 @@ class GongzhonghaoAuthor:
|
|
|
Common.logger(log_type, crawler).info(f'标题相似度>=80%:{video_dict["video_title"]}\n')
|
|
|
Common.logging(log_type, crawler, env, f'标题相似度>=80%:{video_dict["video_title"]}\n')
|
|
|
else:
|
|
|
- # cls.download_publish(log_type=log_type,
|
|
|
- # crawler=crawler,
|
|
|
- # video_dict=video_dict,
|
|
|
- # rule_dict=rule_dict,
|
|
|
- # # user_dict=user_dict,
|
|
|
- # env=env)
|
|
|
video_dict["out_user_id"] = video_dict["user_id"]
|
|
|
video_dict["platform"] = crawler
|
|
|
video_dict["strategy"] = log_type
|
|
@@ -338,6 +333,7 @@ class GongzhonghaoAuthor:
|
|
|
video_dict["user_id"] = user_dict["uid"] # 站内 UID?爬虫获取不到了(随机发布到原 5 个账号中)
|
|
|
video_dict["publish_time"] = video_dict["publish_time_str"]
|
|
|
mq.send_msg(video_dict)
|
|
|
+ time.sleep(random.randint(1, 3))
|
|
|
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")
|
|
@@ -353,133 +349,6 @@ class GongzhonghaoAuthor:
|
|
|
return len(repeat_video)
|
|
|
|
|
|
# 下载/上传
|
|
|
- @classmethod
|
|
|
- def download_publish(cls, log_type, crawler, video_dict, rule_dict, env):
|
|
|
- # 下载视频
|
|
|
- Common.download_method(log_type=log_type, crawler=crawler, text="video", title=video_dict["video_title"], url=video_dict["video_url"])
|
|
|
- md_title = md5(video_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
|
|
|
- # 获取视频时长
|
|
|
- ffmpeg_dict = Common.ffmpeg(log_type, crawler, f"./{crawler}/videos/{video_dict['video_title']}/video.mp4")
|
|
|
- video_dict["video_width"] = ffmpeg_dict["width"]
|
|
|
- video_dict["video_height"] = ffmpeg_dict["height"]
|
|
|
- video_dict["duration"] = ffmpeg_dict["duration"]
|
|
|
- Common.logger(log_type, crawler).info(f'video_width:{video_dict["video_width"]}')
|
|
|
- Common.logging(log_type, crawler, env, f'video_width:{video_dict["video_width"]}')
|
|
|
- Common.logger(log_type, crawler).info(f'video_height:{video_dict["video_height"]}')
|
|
|
- Common.logging(log_type, crawler, env, f'video_height:{video_dict["video_height"]}')
|
|
|
- Common.logger(log_type, crawler).info(f'duration:{video_dict["duration"]}')
|
|
|
- Common.logging(log_type, crawler, env, f'duration:{video_dict["duration"]}')
|
|
|
- if download_rule(log_type, crawler, video_dict, rule_dict) is False:
|
|
|
- shutil.rmtree(f"./{crawler}/videos/{md_title}")
|
|
|
- Common.logger(log_type, crawler).info("不满足抓取规则,删除成功\n")
|
|
|
- Common.logging(log_type, crawler, env, "不满足抓取规则,删除成功\n")
|
|
|
- return
|
|
|
- # 下载封面
|
|
|
- Common.download_method(log_type=log_type, crawler=crawler, text="cover",
|
|
|
- title=video_dict["video_title"], url=video_dict["cover_url"])
|
|
|
- # 保存视频信息至 "./videos/{video_title}/info.txt"
|
|
|
- Common.save_video_info(log_type=log_type, crawler=crawler, video_dict=video_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...")
|
|
|
- strategy = "定向爬虫策略"
|
|
|
- if env == 'prod':
|
|
|
- oss_endpoint = "inner"
|
|
|
- our_video_id = Publish.upload_and_publish(log_type=log_type,
|
|
|
- crawler=crawler,
|
|
|
- strategy=strategy,
|
|
|
- our_uid="follow",
|
|
|
- oss_endpoint=oss_endpoint,
|
|
|
- env=env)
|
|
|
- our_video_link = f"https://admin.piaoquantv.com/cms/post-detail/{str(our_video_id)}/info"
|
|
|
- else:
|
|
|
- oss_endpoint = "out"
|
|
|
- our_video_id = Publish.upload_and_publish(log_type=log_type,
|
|
|
- crawler=crawler,
|
|
|
- strategy=strategy,
|
|
|
- our_uid="follow",
|
|
|
- oss_endpoint=oss_endpoint,
|
|
|
- env=env)
|
|
|
- our_video_link = f"https://testadmin.piaoquantv.com/cms/post-detail/{str(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_dict['user_id']}",
|
|
|
- "{cls.platform}",
|
|
|
- "定向爬虫策略",
|
|
|
- "{video_dict['video_id']}",
|
|
|
- "{video_dict['video_title']}",
|
|
|
- "{video_dict['cover_url']}",
|
|
|
- "{video_dict['video_url']}",
|
|
|
- {int(video_dict['duration'])},
|
|
|
- "{video_dict['publish_time_str']}",
|
|
|
- {int(video_dict['play_cnt'])},
|
|
|
- '{json.dumps(rule_dict)}',
|
|
|
- {int(video_dict['video_width'])},
|
|
|
- {int(video_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('视频信息写入数据库成功')
|
|
|
- Common.logging(log_type, crawler, env, '视频信息写入数据库成功')
|
|
|
-
|
|
|
- # 视频写入飞书
|
|
|
- Feishu.insert_columns(log_type, crawler, "47e39d", "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)),
|
|
|
- "用户主页",
|
|
|
- video_dict['video_title'],
|
|
|
- video_dict['video_id'],
|
|
|
- our_video_link,
|
|
|
- int(video_dict['duration']),
|
|
|
- f"{video_dict['video_width']}*{video_dict['video_height']}",
|
|
|
- video_dict['publish_time_str'],
|
|
|
- video_dict['user_name'],
|
|
|
- video_dict['user_id'],
|
|
|
- video_dict['avatar_url'],
|
|
|
- video_dict['cover_url'],
|
|
|
- video_dict['article_url'],
|
|
|
- video_dict['video_url']]]
|
|
|
- time.sleep(0.5)
|
|
|
- Feishu.update_values(log_type, crawler, "47e39d", "F2:Z2", values)
|
|
|
- Common.logger(log_type, crawler).info('视频下载/上传成功\n')
|
|
|
- Common.logging(log_type, crawler, env, '视频下载/上传成功\n')
|
|
|
|
|
|
@classmethod
|
|
|
def get_all_videos(cls, log_type, crawler, task_dict, token_index, rule_dict, user_list, env):
|