crawler_haokan/main/haokan_hot.py

# -*- coding: utf-8 -*-
# @Author: wangkun
# @Time: 2022/11/23
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 Hot:

    page = 0

    @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_hot_feeds(cls, log_type, our_id, env):
        try:
            while True:
                cls.page += 1
                url = 'https://haokan.baidu.com/videoui/page/pc/toplist?'
                headers = {
                    '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',
                    'Content-Type': 'application/x-www-form-urlencoded',
                    'Cookie': 'BIDUPSID=0C817797C726E2312710D870ECDAE8A2; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; PSTM=1669001132; BAIDUID=AB7069CAF9ECB7AA43E400D164119733:FG=1; BDSFRCVID=H54OJexroG0GmHrjfnewtKf1EeKK0gOTDYLEJs2qYShnrsPVJeC6EG0PtoWQkz--EHtdogKK0mOTHv8F_2uxOjjg8UtVJeC6EG0Ptf8g0M5; H_BDCLCKID_SF=tR333R7oKRu_HRjYbb__-P4DePAttURZ56bHWh0M3b61qRcIh4ob5MPEDto-BMPj52OnKUT13lc5h4jX0P7_KRtr346-35543bRTLn76LRv0Kj6HybOfhP-UyN3LWh37bJblMKoaMp78jR093JO4y4Ldj4oxJpOJ5JbMopCafJOKHICGDTA-jMK; Hm_lvt_4aadd610dfd2f5972f1efee2653a2bc5=1669029805; PC_TAB_LOG=video_details_page; COMMON_LID=88bc9b0fbce964fbb6a76cfd7927d02b; hkpcvideolandquery=%u4E2D%u56FD%u7537%u513F%u5218%u5F3A%u6012%u70E7%u9756%u56FD%u795E%u793E%uFF0C%u518D%u70E7%u65E5%u672C%u9A7B%u97E9%u5927%u4F7F%u9986%uFF0C%u540E%u6765%u600E%u4E48%u6837%u4E86%uFF1F; BDSFRCVID_BFESS=H54OJexroG0GmHrjfnewtKf1EeKK0gOTDYLEJs2qYShnrsPVJeC6EG0PtoWQkz--EHtdogKK0mOTHv8F_2uxOjjg8UtVJeC6EG0Ptf8g0M5; H_BDCLCKID_SF_BFESS=tR333R7oKRu_HRjYbb__-P4DePAttURZ56bHWh0M3b61qRcIh4ob5MPEDto-BMPj52OnKUT13lc5h4jX0P7_KRtr346-35543bRTLn76LRv0Kj6HybOfhP-UyN3LWh37bJblMKoaMp78jR093JO4y4Ldj4oxJpOJ5JbMopCafJOKHICGDTA-jMK; H_PS_PSSID=36557_37769_34813_37778_37728_36806_37719_37743_26350_37787; PSINO=2; delPer=0; BA_HECTOR=8la125a48ka00la4agal0he91hnre381e; BAIDUID_BFESS=AB7069CAF9ECB7AA43E400D164119733:FG=1; ZFY=e8fgayH:A:A8S2QAjzqo6RRIm7t3wLMhAdtluiJeCoSc4:C; Hm_lpvt_4aadd610dfd2f5972f1efee2653a2bc5=1669206505; ariaDefaultTheme=undefined; RT="z=1&dm=baidu.com&si=7jsviskg99&ss=latmgdwn&sl=1&tt=10y&bcn=https%3A%2F%2Ffclog.baidu.com%2Flog%2Fweirwood%3Ftype%3Dperf&ld=1tl"',
                    'Pragma': 'no-cache',
                    'Referer': 'https://haokan.baidu.com/',
                    '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/107.0.1418.52',
                    '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"'
                }
                params = {
                    'type': 'hotvideo',
                    'sfrom': 'haokan_web_banner',
                    'pageSize': '20',
                    '_format': 'json',
                    'page': str(cls.page)
                }
                urllib3.disable_warnings()
                r = requests.get(url=url, headers=headers, params=params, verify=False)
                if r.json()['errno'] != 0 or r.json()['error'] != '成功':
                    Common.logger(log_type).error(f'feeds_response:{r.text}\n')
                elif len(r.json()['apiData']['response']['video']) == 0:
                    Common.logger(log_type).info(f'没有新数据了\n')
                    return
                else:
                    feeds = r.json()['apiData']['response']['video']
                    Common.logger(log_type).info(f'正在抓取第{cls.page}页\n')
                    for i in range(len(feeds)):
                        # video_title
                        if 'title' not in feeds[i]:
                            video_title = 0
                        else:
                            video_title = feeds[i]['title']

                        # video_id
                        if 'vid' not in feeds[i]:
                            video_id = 0
                        else:
                            video_id = feeds[i]['vid']

                        # duration
                        if 'duration' not in feeds[i]:
                            duration = 0
                        else:
                            duration = feeds[i]['duration']

                        # publish_time
                        if 'publish_time' not in feeds[i]:
                            publish_time = 0
                        else:
                            publish_time = feeds[i]['publish_time']\
                                .replace('发布时间：', '').replace('年', '/').replace('月', '/').replace('日', '')

                        # user_name
                        if 'author' not in feeds[i]:
                            user_name = 0
                        else:
                            user_name = feeds[i]['author']

                        # head_url
                        if 'author_icon' not in feeds[i]:
                            head_url = 0
                        else:
                            head_url = feeds[i]['author_icon']

                        # cover_url
                        if 'poster' not in feeds[i]:
                            cover_url = 0
                        else:
                            cover_url = feeds[i]['poster']

                        # video_url
                        get_video_url = cls.get_video_url(log_type, video_id)
                        if get_video_url is not None:
                            video_url = get_video_url
                        elif 'videoUrl' in feeds[i]:
                            video_url = feeds[i]['videoUrl']
                        else:
                            video_url = 0

                        Common.logger(log_type).info(f'video_title:{video_title}')
                        Common.logger(log_type).info(f'video_id:{video_id}')
                        Common.logger(log_type).info(f'duration:{duration}')
                        Common.logger(log_type).info(f'publish_time:{publish_time}')
                        Common.logger(log_type).info(f'user_name:{user_name}')
                        Common.logger(log_type).info(f'head_url:{head_url}')
                        Common.logger(log_type).info(f'cover_url:{cover_url}')
                        Common.logger(log_type).info(f'video_url:{video_url}\n')

                        video_dict = {'video_title': video_title,
                                      'video_id': video_id,
                                      'duration': duration,
                                      'publish_time': publish_time,
                                      'user_name': user_name,
                                      'head_url': head_url,
                                      'cover_url': cover_url,
                                      'video_url': video_url}
                        cls.download_publish(log_type, video_dict, our_id, env)

                    time.sleep(5)
        except Exception as e:
            Common.logger(log_type).error(f'get_hot_feeds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:
                Common.logger(log_type).info(f'get_video_url_response:{r.text}')
            elif r.json()['errno'] != 0 or len(r.json()['data']) == 0:
                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']

                return video_url
        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):
        if video_dict['video_title'] == 0 or video_dict['video_url'] == 0:
            Common.logger(log_type).info('无效视频\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', 'A5VCbq') 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')
        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']) + "\n" +
                          '0' + "\n" +
                          '0' + "\n" +
                          '0' + "\n" +
                          '0' + "\n" +
                          '1920*1080' + "\n" +
                          str(int(time.mktime(time.strptime(video_dict['publish_time'], "%Y/%m/%d")))) + "\n" +
                          str(video_dict['user_name']) + "\n" +
                          str(video_dict['head_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", "5pWipX", "ROWS", 1, 2)
            upload_time = int(time.time())
            values = [[time.strftime("%Y/%m/%d %H:%M:%S", time.localtime(upload_time)),
                       "今日热播榜",
                       video_dict['video_title'],
                       video_dict['video_id'],
                       our_video_link,
                       video_dict['duration'],
                       video_dict['publish_time'],
                       video_dict['user_name'],
                       video_dict['head_url'],
                       video_dict['cover_url'],
                       video_dict['video_url']]]
            time.sleep(1)
            Feishu.update_values(log_type, "haokan", "5pWipX", "F2:Z2", values)
            Common.logger(log_type).info(f"视频:{video_dict['video_title']}，下载/上传成功\n")


if __name__ == '__main__':
    Hot.get_hot_feeds('hot', '6267140', 'dev')

    pass