crawler_haokan/main/haokan_follow.py

# -*- coding: utf-8 -*-
# @Author: wangkun
# @Time: 2023/1/13
import datetime
import os
import sys
import time
import requests
import urllib3
sys.path.append(os.getcwd())
from main.common import Common
from main.feishu_lib import Feishu
from main.haokan_publish import Publish


class Follow:
    ctime = ''

    @classmethod
    def filter_words(cls, log_type):
        try:
            filter_words_sheet = Feishu.get_values_batch(log_type, 'haokan', 'nKgHzp')
            filter_words_list = []
            for x in filter_words_sheet:
                for y in x:
                    if y is None:
                        pass
                    else:
                        filter_words_list.append(y)
            return filter_words_list
        except Exception as e:
            Common.logger(log_type).error(f'filter_words异常:{e}')

    @classmethod
    def get_users_from_feishu(cls, log_type):
        try:
            user_sheet = Feishu.get_values_batch(log_type, 'haokan', 'x4nb7H')
            user_dict = {}
            for i in range(1, len(user_sheet)):
                user_name = user_sheet[i][0]
                out_id = user_sheet[i][1]
                our_id = user_sheet[i][3]
                if user_name is None or out_id is None or our_id is None:
                    pass
                else:
                    user_dict[user_name] = str(out_id) + ',' + str(our_id)
            return user_dict
        except Exception as e:
            Common.logger(log_type).error(f'get_users_from_feishu异常:{e}\n')

    @classmethod
    def follow_download_rule(cls, duration, width, height):
        if int(duration) >= 40:
            if int(width) >= 0 or int(height) >= 0:
                return True
            else:
                return False
        else:
            return False

    @classmethod
    def get_follow_feed(cls, log_type, out_id, our_id, user_name, env):
        try:
            while True:
                url = 'https://haokan.baidu.com/web/author/listall?'
                headers = {
                    'Accept': '*/*',
                    'Accept-Encoding': 'gzip, deflate, br',
                    'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
                    'Cache-Control': 'no-cache',
                    'Connection': 'keep-alive',
                    'Content-Type': 'application/x-www-form-urlencoded',
                    'Cookie': Feishu.get_values_batch(log_type, 'haokan', '5LksMx')[0][0],
                    'Referer': 'https://haokan.baidu.com/author/'+str(out_id),
                    'Pragma': 'no-cache',
                    'Host': 'haokan.baidu.com',
                    'sec-ch-ua': '"Not?A_Brand";v="8", "Chromium";v="108", "Microsoft Edge";v="108"',
                    'sec-ch-ua-mobile': '?0',
                    'sec-ch-ua-platform': '"macOS"',
                    'Sec-Fetch-Dest': 'empty',
                    'Sec-Fetch-Mode': 'cors',
                    'Sec-Fetch-Site': 'same-origin',
                    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36 Edg/108.0.1462.76'
                }
                params = {
                    'app_id': str(out_id),
                    'ctime': cls.ctime,
                    'rn': '10',
                    'searchAfter': '',
                    '_api': '1'
                }
                response = requests.get(url=url, headers=headers, params=params, verify=False)
                if '"errno":0,' not in response.text:
                    Common.logger(log_type).warning(f'get_follow_feed:{response.text}\n')
                    return
                elif len(response.json()['data']['results']) == 0:
                    Common.logger(log_type).info(f'get_follow_feed:{response.json()}\n')
                    cls.ctime = 0
                    return
                else:
                    cls.ctime = response.json()['data']['ctime']

                    follow_feeds = response.json()['data']['results']
                    for i in range(len(follow_feeds)):
                        # video_title
                        if 'title' not in follow_feeds[i]['content']:
                            video_title = ''
                        else:
                            video_title = follow_feeds[i]['content']['title']

                        # video_id
                        if 'vid' not in follow_feeds[i]['content']:
                            video_id = ''
                        else:
                            video_id = follow_feeds[i]['content']['vid']

                        # is_top
                        if 'is_show_feature' not in follow_feeds[i]['content']:
                            is_top = ''
                        else:
                            is_top = follow_feeds[i]['content']['is_show_feature']

                        # play_cnt
                        if 'playcnt' not in follow_feeds[i]['content']:
                            play_cnt = ''
                        else:
                            play_cnt = follow_feeds[i]['content']['playcnt']

                        # duration
                        if 'duration' not in follow_feeds[i]['content']:
                            duration = ''
                            duration_stamp = ''
                        else:
                            duration = follow_feeds[i]['content']['duration']
                            duration_stamp = int(duration.split(':')[0])*60 + int(duration.split(':')[-1])

                        # publish_time
                        if 'publish_time' not in follow_feeds[i]['content']:
                            publish_time = ''
                        else:
                            publish_time = follow_feeds[i]['content']['publish_time']

                        # publish_time_stamp
                        if '刚刚' in publish_time:
                            publish_time_stamp = int(time.time())
                        elif '分钟前' in publish_time:
                            publish_time_stamp = int(time.time()) - int(publish_time[0]) * 60
                        elif '小时前' in publish_time:
                            publish_time_stamp = int(time.time()) - int(publish_time[0]) * 3600
                        elif '昨天' in publish_time:
                            publish_time_str = (datetime.date.today() + datetime.timedelta(days=-1)).strftime("%Y/%m/%d")
                            publish_time_stamp = int(time.mktime(time.strptime(publish_time_str, "%Y/%m/%d")))
                        elif '天前' in publish_time:
                            today = datetime.date.today()
                            publish_time_str = today - datetime.timedelta(days=int(publish_time[0]))
                            publish_time_stamp = int(time.mktime(publish_time_str.timetuple()))
                        elif '年' in publish_time:
                            publish_time_str = publish_time.replace('年', '/').replace('月', '/').replace('日', '')
                            publish_time_stamp = int(time.mktime(time.strptime(publish_time_str, "%Y/%m/%d")))
                        else:
                            publish_time_str = publish_time.replace('月', '/').replace('日', '')
                            this_year = datetime.datetime.now().year
                            publish_time_stamp = int(time.mktime(time.strptime(f"{this_year}/{publish_time_str}", "%Y/%m/%d")))

                        # cover_url
                        if 'cover_src' in follow_feeds[i]['content']:
                            cover_url = follow_feeds[i]['content']['cover_src']
                        elif 'cover_src_pc' in follow_feeds[i]['content']:
                            cover_url = follow_feeds[i]['content']['cover_src_pc']
                        elif 'poster' in follow_feeds[i]['content']:
                            cover_url = follow_feeds[i]['content']['poster']
                        else:
                            cover_url = ''

                        if is_top is True and int(time.time()) - publish_time_stamp >= 3600*24*30:
                            Common.logger(log_type).info(f'video_title:{video_title}')
                            Common.logger(log_type).info(f'置顶视频，发布时间超过30天:{publish_time}\n')
                        elif int(time.time()) - publish_time_stamp >= 3600*24*30:
                            Common.logger(log_type).info(f'video_title:{video_title}')
                            Common.logger(log_type).info(f'发布时间超过30天:{publish_time}\n')
                            cls.ctime = ''
                            return
                        else:
                            video_info_dict = cls.get_video_url(log_type, video_id)
                            # video_url
                            video_url = video_info_dict['video_url']
                            # video_width
                            video_width = video_info_dict['video_width']
                            # video_height
                            video_height = video_info_dict['video_height']

                            Common.logger(log_type).info(f'video_title:{video_title}')
                            # Common.logger(log_type).info(f'user_name:{user_name}')
                            # Common.logger(log_type).info(f'out_id:{out_id}')
                            # Common.logger(log_type).info(f'our_id:{our_id}')
                            # Common.logger(log_type).info(f'duration_stamp:{duration_stamp}')
                            Common.logger(log_type).info(f'duration:{duration}')
                            Common.logger(log_type).info(f'video_width:{video_width}')
                            Common.logger(log_type).info(f'video_height:{video_height}')
                            Common.logger(log_type).info(f'publish_time:{publish_time}')
                            Common.logger(log_type).info(f'video_url:{video_url}\n')

                            video_dict = {
                                'video_title': video_title,
                                'video_id': video_id,
                                'play_cnt': play_cnt,
                                'duration': duration,
                                'duration_stamp': duration_stamp,
                                'publish_time': publish_time,
                                'video_width': video_width,
                                'video_height': video_height,
                                'user_name': user_name,
                                'cover_url': cover_url,
                                'video_url': video_url
                            }
                            cls.download_publish(log_type, video_dict, our_id, env)
        except Exception as e:
            Common.logger(log_type).error(f'get_follow_feed异常:{e}\n')

    @classmethod
    def get_video_url(cls, log_type, video_id):
        try:
            url = 'https://haokan.hao123.com/v?'
            params = {
                'vid': str(video_id),
                '_format': 'json',
            }
            headers = {
                'Accept': '*/*',
                'Accept-Encoding': 'gzip, deflate, br',
                'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
                'Cache-Control': 'no-cache',
                'Connection': 'keep-alive',
                'Content-Type': 'application/x-www-form-urlencoded',
                'Cookie': 'PC_TAB_LOG=video_details_page; COMMON_LID=b0be69dd9fcae328d06935bd40f615cd; Hm_lvt_4aadd610dfd2f5972f1efee2653a2bc5=1669029953; hkpcvideolandquery=%u82CF%u5DDE%u6700%u5927%u7684%u4E8C%u624B%u8F66%u8D85%u5E02%uFF0C%u8F6C%u4E00%u8F6C%u91CC%u8FB9%u8C6A%u8F66%u592A%u591A%u4E86%uFF0C%u4EF7%u683C%u66F4%u8BA9%u6211%u5403%u60CA%uFF01; Hm_lpvt_4aadd610dfd2f5972f1efee2653a2bc5=1669875695; ariaDefaultTheme=undefined; reptileData=%7B%22data%22%3A%22636c55e0319da5169a60acec4a264a35c10862f8abfe2f2cc32c55eb6b0ab4de0efdfa115ea522d6d4d361dea07feae2831d3e2c16ed6b051c611ffe5aded6c9f852501759497b9fbd2132a2160e1e40e5845b41f78121ddcc3288bd077ae4e8%22%2C%22key_id%22%3A%2230%22%2C%22sign%22%3A%22f6752aac%22%7D; RT="z=1&dm=hao123.com&si=uc0q7wnm4w&ss=lb4otu71&sl=j&tt=av0&bcn=https%3A%2F%2Ffclog.baidu.com%2Flog%2Fweirwood%3Ftype%3Dperf&ld=1rdw&cl=7v6c"',
                'Pragma': 'no-cache',
                'Referer': 'https://haokan.hao123.com/v?vid=10623278258033022286&pd=pc&context=',
                'sec-ch-ua': '"Microsoft Edge";v="107", "Chromium";v="107", "Not=A?Brand";v="24"',
                'sec-ch-ua-mobile': '?0',
                'sec-ch-ua-platform': '"macOS"',
                'Sec-Fetch-Dest': 'empty',
                'Sec-Fetch-Mode': 'cors',
                'Sec-Fetch-Site': 'same-origin',
                'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36 Edg/107.0.1418.62',
            }
            urllib3.disable_warnings()
            r = requests.get(url=url, headers=headers, params=params, verify=False)
            if r.status_code != 200:
                video_url = ''
                video_width = ''
                video_height = ''
                Common.logger(log_type).info(f'get_video_url_response:{r.text}')
            elif r.json()['errno'] != 0 or len(r.json()['data']) == 0:
                video_url = ''
                video_width = ''
                video_height = ''
                Common.logger(log_type).info(f'get_video_url_response:{r.json()}')
            else:
                clarityUrl = r.json()['data']['apiData']['curVideoMeta']['clarityUrl']
                video_url = r.json()['data']['apiData']['curVideoMeta']['clarityUrl'][len(clarityUrl) - 1]['url']
                video_width = r.json()['data']['apiData']['curVideoMeta']['clarityUrl'][len(clarityUrl) - 1]['vodVideoHW'].split('$$')[-1]
                video_height = r.json()['data']['apiData']['curVideoMeta']['clarityUrl'][len(clarityUrl) - 1]['vodVideoHW'].split('$$')[0]

            video_info_dict = {
                'video_url': video_url,
                'video_width': video_width,
                'video_height': video_height
            }
            return video_info_dict
        except Exception as e:
            Common.logger(log_type).error(f'get_video_url异常:{e}\n')

    @classmethod
    def download_publish(cls, log_type, video_dict, our_id, env):
        try:
            if video_dict['video_title'] == '' or video_dict['video_id'] == '' or video_dict['video_url'] == '':
                Common.logger(log_type).info('无效视频\n')
            elif int(video_dict['duration_stamp']) < 60:
                Common.logger(log_type).info(f'时长:{int(video_dict["duration"])} < 60s\n')
            elif int(video_dict['video_width']) < 720 or int(video_dict['video_height']) < 720:
                Common.logger(log_type).info(f'{int(video_dict["video_width"])}*{int(video_dict["video_height"])} < 720P\n')
            elif any(word if word in video_dict['video_title'] else False for word in cls.filter_words(log_type)) is True:
                Common.logger(log_type).info('已中过滤词库\n')
            elif video_dict['video_id'] in [x for y in Feishu.get_values_batch(log_type, 'haokan', '5pWipX') for x in y]:
                Common.logger(log_type).info('视频已下载\n')
            elif video_dict['video_id'] in [x for y in Feishu.get_values_batch(log_type, 'haokan', '7f05d8') for x in y]:
                Common.logger(log_type).info('视频已下载\n')
            elif video_dict['video_id'] in [x for y in Feishu.get_values_batch(log_type, 'haokan', 'kVaSjf') for x in y]:
                Common.logger(log_type).info('视频已下载\n')
            elif video_dict['video_id'] in [x for y in Feishu.get_values_batch(log_type, 'haokan', 'A5VCbq') for x in y]:
                Common.logger(log_type).info('视频已下载\n')
            else:
                # 下载
                Common.download_method(log_type, 'cover', video_dict['video_title'], video_dict['cover_url'])
                Common.download_method(log_type, 'video', video_dict['video_title'], video_dict['video_url'])
                with open("./videos/" + video_dict['video_title']
                          + "/" + "info.txt", "a", encoding="UTF-8") as f_a:
                    f_a.write(str(video_dict['video_id']) + "\n" +
                              str(video_dict['video_title']) + "\n" +
                              str(video_dict['duration_stamp']) + "\n" +
                              '100000' + "\n" +
                              '100000' + "\n" +
                              '100000' + "\n" +
                              '100000' + "\n" +
                              '1920*1080' + "\n" +
                              str(int(time.time())) + "\n" +
                              str(video_dict['user_name']) + "\n" +
                              str(video_dict['cover_url']) + "\n" +
                              str(video_dict['video_url']) + "\n" +
                              str(video_dict['cover_url']) + "\n" +
                              "HAOKAN" + str(int(time.time())))
                Common.logger(log_type).info("==========视频信息已保存至info.txt==========")

                # 上传
                Common.logger(log_type).info(f"开始上传视频:{video_dict['video_title']}")
                if env == 'dev':
                    our_video_id = Publish.upload_and_publish(log_type, our_id, env)
                    our_video_link = "https://testadmin.piaoquantv.com/cms/post-detail/" + str(our_video_id) + "/info"
                else:
                    our_video_id = Publish.upload_and_publish(log_type, our_id, env)
                    our_video_link = "https://admin.piaoquantv.com/cms/post-detail/" + str(our_video_id) + "/info"
                Common.logger(log_type).info(f"视频上传完成:{video_dict['video_title']}\n")

                # 保存视频信息至云文档
                Common.logger(log_type).info(f"保存视频至已下载表:{video_dict['video_title']}")
                Feishu.insert_columns(log_type, "haokan", "kVaSjf", "ROWS", 1, 2)
                upload_time = int(time.time())
                values = [[time.strftime("%Y/%m/%d %H:%M:%S", time.localtime(upload_time)),
                           '定向榜',
                           video_dict['video_title'],
                           video_dict['video_id'],
                           our_video_link,
                           int(video_dict['play_cnt']),
                           video_dict['duration'],
                           video_dict['publish_time'],
                           video_dict['video_width']+"*"+video_dict['video_height'],
                           video_dict['user_name'],
                           video_dict['cover_url'],
                           video_dict['video_url']]]
                time.sleep(1)
                Feishu.update_values(log_type, "haokan", "kVaSjf", "F2:Z2", values)
                Common.logger(log_type).info(f"视频:{video_dict['video_title']}，下载/上传成功\n")
        except Exception as e:
            Common.logger(log_type).error(f'download_publish异常:{e}\n')

    @classmethod
    def get_user_videos(cls, log_type, env):
        try:
            user_dict = cls.get_users_from_feishu(log_type)
            if len(user_dict) == 0:
                Common.logger(log_type).warning('用户ID列表为空\n')
            else:
                for k, v in user_dict.items():
                    user_name = k
                    out_id = v.split(',')[0]
                    our_id = v.split(',')[1]
                    Common.logger(log_type).info(f'抓取{user_name}主页视频\n')
                    cls.get_follow_feed(log_type, out_id, our_id, user_name, env)
                    Common.logger(log_type).info('休眠 30 秒\n')
                    time.sleep(30)
                    cls.ctime = ''
        except Exception as e:
            Common.logger(log_type).error(f'get_user_videos异常:{e}\n')


if __name__ == '__main__':
    print(Follow.get_users_from_feishu('follow'))
    pass