video_rewriting/data_channel/dy_ls.py

import random
import time

import requests
import json

from common import Common
from common.sql_help import sqlCollect


class DYLS:

    @classmethod
    def get_dyls_list(cls, task_mark, url_id, number, mark):
        next_cursor = ""
        for i in range(50):
            url = "http://8.217.190.241:8888/crawler/dou_yin/blogger"
            payload = json.dumps({
                "account_id": url_id,
                "source": "抖查查",
                "cursor": next_cursor
            })
            headers = {
                'Content-Type': 'application/json'
            }
            time.sleep(random.randint(1, 5))
            response = requests.request("POST", url, headers=headers, data=payload)
            response = response.json()
            list = []
            data_all_list = response["data"]
            has_more = data_all_list["has_more"]
            next_cursor = str(data_all_list["next_cursor"])
            try:
                data_list = data_all_list["data"]
                for data in data_list:
                    # comment_count = data["comment_count"]
                    # download_count = data["download_count"]
                    share_count = data["share_count"]
                    good_count = data["good_count"]
                    # collect_count = data["collect_count"]
                    duration = data["duration"]
                    video_id = data["video_id"]
                    old_title = data["video_desc"]
                    status = sqlCollect.is_used(task_mark, video_id, mark, "抖音")
                    if status:
                        status = sqlCollect.is_used(task_mark, video_id, mark, "抖音历史")
                        if status == False:
                            continue

                        video_percent = '%.2f' % (int(share_count) / int(good_count))
                        special = float(0.25)
                        duration = duration / 1000
                        if int(share_count) < 500 or float(video_percent) < special or int(duration) < 30 or int(duration) > 720:
                            Common.logger("dy-ls").info(
                                f"不符合规则：{task_mark},用户主页id:{url_id},视频id{video_id} ,分享:{share_count},点赞{good_count} ,时长:{int(duration)} ")
                            continue
                        video_url, image_url = cls.get_video(video_id)
                        if video_url:
                            all_data = {"video_id": video_id, "cover": image_url, "video_url": video_url, "rule": video_percent,
                                        "old_title": old_title}
                            list.append(all_data)
                            if len(list) == int(number):
                                Common.logger("dy-ls").info(f"获取抖音历史视频总数:{len(list)}\n")
                                return list
                if has_more == False:
                    return list
            except Exception as exc:
                Common.logger("dy-ls").info(f"抖音历史数据获取失败:{exc}\n")
                return list

    @classmethod
    def get_video(cls, video_id):
        url = "http://8.217.190.241:8888/crawler/dou_yin/detail"

        payload = json.dumps({
            "content_id": str(video_id)
        })
        headers = {
            'Content-Type': 'application/json'
        }

        response = requests.request("POST", url, headers=headers, data=payload)
        response = response.json()
        data = response["data"]["data"]
        video_url = data["video_url_list"][0]["video_url"]
        image_url = data["image_url_list"][0]["image_url"]
        return video_url, image_url



if __name__ == '__main__':
    # DYLS.get_video("7314923922602954022")
    DYLS.get_dyls_list("1","MS4wLjABAAAA2QEvnEb7cQDAg6vZXq3j8_LlbO_DiturnV7VeybFKY4",1,"1")