用python开发的抖音关键词搜索采集软件

# 请求地址
url = 'https://www.douyin.com/aweme/v1/web/search/item/'

# 请求头
h1 = {
	"Accept": 'application/json, text/plain, */*',
	"Accept-Encoding": "gzip, deflate",
	"Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
	"Cookie": self.cookie_val,
	"Referer": "",
	"Sec-Ch-Ua": 'Not_A Brand";v="8", "Chromium";v="120", "Google Chrome";v="120',
	"Sec-Ch-Ua-Mobile": "?0",
	"Sec-Ch-Ua-Platform": "Windows",
	"Sec-Fetch-Dest": "empty",
	"Sec-Fetch-Mode": "cors",
	"Sec-Fetch-Site": "same-origin",
	"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
}

# 请求参数
params = {
	"device_platform": "webapp",
	"aid": "6383",
	"channel": "channel_pc_web",
	"search_channel": "aweme_video_web",
	"sort_type": self.trans_sort_type(v_str=self.sort_type),
	"publish_time": self.trans_time_range(v_str=self.time_range),
	"keyword": search_keyword,
	"search_source": "tab_search",
	"query_correct_type": "1",
	"is_filter_search": "1",
	"from_group_id": "",
	"offset": cursor,
	"count": "20",
	"pc_client_type": "1",
	"version_code": "170400",
	"version_name": "17.4.0",
	"cookie_enabled": "true",
	"screen_width": "1536",
	"screen_height": "864",
	"browser_language": "zh-CN",
	"browser_platform": "Win32",
	"browser_name": "Chrome",
	"browser_version": "120.0.0.0",
	"browser_online": "true",
	"engine_name": "Blink",
	"engine_version": "120.0.0.0",
	"os_name": "Windows",
	"os_version": "10",
	"cpu_core_num": "8",
	"device_memory": "8",
	"platform": "PC",
	"downlink": "10",
	"effective_type": "4g",
	"round_trip_time": "50",
	"webid": "7249265465250973217",
	"msToken": "Sx2PzLIz0YGvM_wrIkaUaaeUb1JUutgo3ERiWmwV1w6VC1naW15lFM6N3nanMZRZYfaHLvXrDNzGqkAyvvCpdO3d6u0u_kNmmZZHeMIsDqga2eWnjTzp5g==",
	"X-Bogus": ""
}

# 发送请求
r = requests.get(url, headers=h1, params=params)
# 以json格式接收返回数据
json_data = r.json()

for v in video_list:
	# 视频标题
	title = v['aweme_info']['desc']
	self.tk_show('视频标题:' + title)
	title_list.append(title)

# 保存数据到DF
df = pd.DataFrame(
	{
		'关键词': search_keyword,
		'页码': page,
		'视频标题': title_list,
		'视频链接': link_list,
		'作者昵称': author_name_list,
		'抖音号': author_id_list,
		'作者链接': author_link_list,
		'作者粉丝数': follower_count_list,
		'发布时间': create_time_list,
		'点赞数': like_count_list,
		'评论数': comment_count_list,
		'收藏数': collect_count_list,
		'转发数': share_count_list,
	}
)
df.to_csv(self.result_file, mode='a+', index=False, header=header, encoding='utf_8_sig')
self.tk_show('保存csv文件成功')

def get_logger(self):
	self.logger = logging.getLogger(__name__)
	# 日志格式
	formatter = '[%(asctime)s-%(filename)s][%(funcName)s-%(lineno)d]--%(message)s'
	# 日志级别
	self.logger.setLevel(logging.DEBUG)
	# 控制台日志
	sh = logging.StreamHandler()
	log_formatter = logging.Formatter(formatter, datefmt='%Y-%m-%d %H:%M:%S')
	# info日志文件名
	info_file_name = time.strftime("%Y-%m-%d") + '.log'
	# 将其保存到特定目录，ap方法就是寻找项目根目录，该方法博主前期已经写好。
	case_dir = r'./logs/'
	info_handler = TimedRotatingFileHandler(filename=case_dir + info_file_name,
						when='MIDNIGHT',
						interval=1,
						backupCount=7,
						encoding='utf-8')