The framework has been restructured again, and the Flask framework has been abandoned.
This commit is contained in:
戒酒的李白
@@ -1,266 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : relakkes@gmail.com
|
||||
# @Time : 2024/1/14 18:46
|
||||
# @Desc :
|
||||
from typing import List
|
||||
|
||||
import config
|
||||
from var import source_keyword_var
|
||||
|
||||
from .douyin_store_impl import *
|
||||
from .douyin_store_media import *
|
||||
|
||||
|
||||
class DouyinStoreFactory:
|
||||
STORES = {
|
||||
"csv": DouyinCsvStoreImplement,
|
||||
"db": DouyinDbStoreImplement,
|
||||
"json": DouyinJsonStoreImplement,
|
||||
"sqlite": DouyinSqliteStoreImplement,
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def create_store() -> AbstractStore:
|
||||
store_class = DouyinStoreFactory.STORES.get(config.SAVE_DATA_OPTION)
|
||||
if not store_class:
|
||||
raise ValueError("[DouyinStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite ...")
|
||||
return store_class()
|
||||
|
||||
|
||||
def _extract_note_image_list(aweme_detail: Dict) -> List[str]:
|
||||
"""
|
||||
提取笔记图片列表
|
||||
|
||||
Args:
|
||||
aweme_detail (Dict): 抖音内容详情
|
||||
|
||||
Returns:
|
||||
List[str]: 笔记图片列表
|
||||
"""
|
||||
images_res: List[str] = []
|
||||
images: List[Dict] = aweme_detail.get("images", [])
|
||||
|
||||
if not images:
|
||||
return []
|
||||
|
||||
for image in images:
|
||||
image_url_list = image.get("url_list", []) # download_url_list 为带水印的图片，url_list 为无水印的图片
|
||||
if image_url_list:
|
||||
images_res.append(image_url_list[-1])
|
||||
|
||||
return images_res
|
||||
|
||||
|
||||
def _extract_comment_image_list(comment_item: Dict) -> List[str]:
|
||||
"""
|
||||
提取评论图片列表
|
||||
|
||||
Args:
|
||||
comment_item (Dict): 抖音评论
|
||||
|
||||
Returns:
|
||||
List[str]: 评论图片列表
|
||||
"""
|
||||
images_res: List[str] = []
|
||||
image_list: List[Dict] = comment_item.get("image_list", [])
|
||||
|
||||
if not image_list:
|
||||
return []
|
||||
|
||||
for image in image_list:
|
||||
image_url_list = image.get("origin_url", {}).get("url_list", [])
|
||||
if image_url_list and len(image_url_list) > 1:
|
||||
images_res.append(image_url_list[1])
|
||||
|
||||
return images_res
|
||||
|
||||
|
||||
def _extract_content_cover_url(aweme_detail: Dict) -> str:
|
||||
"""
|
||||
提取视频封面地址
|
||||
|
||||
Args:
|
||||
aweme_detail (Dict): 抖音内容详情
|
||||
|
||||
Returns:
|
||||
str: 视频封面地址
|
||||
"""
|
||||
res_cover_url = ""
|
||||
|
||||
video_item = aweme_detail.get("video", {})
|
||||
raw_cover_url_list = (video_item.get("raw_cover", {}) or video_item.get("origin_cover", {})).get("url_list", [])
|
||||
if raw_cover_url_list and len(raw_cover_url_list) > 1:
|
||||
res_cover_url = raw_cover_url_list[1]
|
||||
|
||||
return res_cover_url
|
||||
|
||||
|
||||
def _extract_video_download_url(aweme_detail: Dict) -> str:
|
||||
"""
|
||||
提取视频下载地址
|
||||
|
||||
Args:
|
||||
aweme_detail (Dict): 抖音视频
|
||||
|
||||
Returns:
|
||||
str: 视频下载地址
|
||||
"""
|
||||
video_item = aweme_detail.get("video", {})
|
||||
url_h264_list = video_item.get("play_addr_h264", {}).get("url_list", [])
|
||||
url_256_list = video_item.get("play_addr_256", {}).get("url_list", [])
|
||||
url_list = video_item.get("play_addr", {}).get("url_list", [])
|
||||
actual_url_list = url_h264_list or url_256_list or url_list
|
||||
if not actual_url_list or len(actual_url_list) < 2:
|
||||
return ""
|
||||
return actual_url_list[-1]
|
||||
|
||||
|
||||
def _extract_music_download_url(aweme_detail: Dict) -> str:
|
||||
"""
|
||||
提取音乐下载地址
|
||||
|
||||
Args:
|
||||
aweme_detail (Dict): 抖音视频
|
||||
|
||||
Returns:
|
||||
str: 音乐下载地址
|
||||
"""
|
||||
music_item = aweme_detail.get("music", {})
|
||||
play_url = music_item.get("play_url", {})
|
||||
music_url = play_url.get("uri", "")
|
||||
return music_url
|
||||
|
||||
|
||||
async def update_douyin_aweme(aweme_item: Dict):
|
||||
aweme_id = aweme_item.get("aweme_id")
|
||||
user_info = aweme_item.get("author", {})
|
||||
interact_info = aweme_item.get("statistics", {})
|
||||
save_content_item = {
|
||||
"aweme_id": aweme_id,
|
||||
"aweme_type": str(aweme_item.get("aweme_type")),
|
||||
"title": aweme_item.get("desc", ""),
|
||||
"desc": aweme_item.get("desc", ""),
|
||||
"create_time": aweme_item.get("create_time"),
|
||||
"user_id": user_info.get("uid"),
|
||||
"sec_uid": user_info.get("sec_uid"),
|
||||
"short_user_id": user_info.get("short_id"),
|
||||
"user_unique_id": user_info.get("unique_id"),
|
||||
"user_signature": user_info.get("signature"),
|
||||
"nickname": user_info.get("nickname"),
|
||||
"avatar": user_info.get("avatar_thumb", {}).get("url_list", [""])[0],
|
||||
"liked_count": str(interact_info.get("digg_count")),
|
||||
"collected_count": str(interact_info.get("collect_count")),
|
||||
"comment_count": str(interact_info.get("comment_count")),
|
||||
"share_count": str(interact_info.get("share_count")),
|
||||
"ip_location": aweme_item.get("ip_label", ""),
|
||||
"last_modify_ts": utils.get_current_timestamp(),
|
||||
"aweme_url": f"https://www.douyin.com/video/{aweme_id}",
|
||||
"cover_url": _extract_content_cover_url(aweme_item),
|
||||
"video_download_url": _extract_video_download_url(aweme_item),
|
||||
"music_download_url": _extract_music_download_url(aweme_item),
|
||||
"note_download_url": ",".join(_extract_note_image_list(aweme_item)),
|
||||
"source_keyword": source_keyword_var.get(),
|
||||
}
|
||||
utils.logger.info(f"[store.douyin.update_douyin_aweme] douyin aweme id:{aweme_id}, title:{save_content_item.get('title')}")
|
||||
await DouyinStoreFactory.create_store().store_content(content_item=save_content_item)
|
||||
|
||||
|
||||
async def batch_update_dy_aweme_comments(aweme_id: str, comments: List[Dict]):
|
||||
if not comments:
|
||||
return
|
||||
for comment_item in comments:
|
||||
await update_dy_aweme_comment(aweme_id, comment_item)
|
||||
|
||||
|
||||
async def update_dy_aweme_comment(aweme_id: str, comment_item: Dict):
|
||||
comment_aweme_id = comment_item.get("aweme_id")
|
||||
if aweme_id != comment_aweme_id:
|
||||
utils.logger.error(f"[store.douyin.update_dy_aweme_comment] comment_aweme_id: {comment_aweme_id} != aweme_id: {aweme_id}")
|
||||
return
|
||||
user_info = comment_item.get("user", {})
|
||||
comment_id = comment_item.get("cid")
|
||||
parent_comment_id = comment_item.get("reply_id", "0")
|
||||
avatar_info = (user_info.get("avatar_medium", {}) or user_info.get("avatar_300x300", {}) or user_info.get("avatar_168x168", {}) or user_info.get("avatar_thumb", {}) or {})
|
||||
save_comment_item = {
|
||||
"comment_id": comment_id,
|
||||
"create_time": comment_item.get("create_time"),
|
||||
"ip_location": comment_item.get("ip_label", ""),
|
||||
"aweme_id": aweme_id,
|
||||
"content": comment_item.get("text"),
|
||||
"user_id": user_info.get("uid"),
|
||||
"sec_uid": user_info.get("sec_uid"),
|
||||
"short_user_id": user_info.get("short_id"),
|
||||
"user_unique_id": user_info.get("unique_id"),
|
||||
"user_signature": user_info.get("signature"),
|
||||
"nickname": user_info.get("nickname"),
|
||||
"avatar": avatar_info.get("url_list", [""])[0],
|
||||
"sub_comment_count": str(comment_item.get("reply_comment_total", 0)),
|
||||
"like_count": (comment_item.get("digg_count") if comment_item.get("digg_count") else 0),
|
||||
"last_modify_ts": utils.get_current_timestamp(),
|
||||
"parent_comment_id": parent_comment_id,
|
||||
"pictures": ",".join(_extract_comment_image_list(comment_item)),
|
||||
}
|
||||
utils.logger.info(f"[store.douyin.update_dy_aweme_comment] douyin aweme comment: {comment_id}, content: {save_comment_item.get('content')}")
|
||||
|
||||
await DouyinStoreFactory.create_store().store_comment(comment_item=save_comment_item)
|
||||
|
||||
|
||||
async def save_creator(user_id: str, creator: Dict):
|
||||
user_info = creator.get("user", {})
|
||||
gender_map = {0: "未知", 1: "男", 2: "女"}
|
||||
avatar_uri = user_info.get("avatar_300x300", {}).get("uri")
|
||||
local_db_item = {
|
||||
"user_id": user_id,
|
||||
"nickname": user_info.get("nickname"),
|
||||
"gender": gender_map.get(user_info.get("gender"), "未知"),
|
||||
"avatar": f"https://p3-pc.douyinpic.com/img/{avatar_uri}" + r"~c5_300x300.jpeg?from=2956013662",
|
||||
"desc": user_info.get("signature"),
|
||||
"ip_location": user_info.get("ip_location"),
|
||||
"follows": user_info.get("following_count", 0),
|
||||
"fans": user_info.get("max_follower_count", 0),
|
||||
"interaction": user_info.get("total_favorited", 0),
|
||||
"videos_count": user_info.get("aweme_count", 0),
|
||||
"last_modify_ts": utils.get_current_timestamp(),
|
||||
}
|
||||
utils.logger.info(f"[store.douyin.save_creator] creator:{local_db_item}")
|
||||
await DouyinStoreFactory.create_store().store_creator(local_db_item)
|
||||
|
||||
|
||||
async def update_dy_aweme_image(aweme_id, pic_content, extension_file_name):
|
||||
"""
|
||||
更新抖音笔记图片
|
||||
Args:
|
||||
aweme_id:
|
||||
pic_content:
|
||||
extension_file_name:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
await DouYinImage().store_image({"aweme_id": aweme_id, "pic_content": pic_content, "extension_file_name": extension_file_name})
|
||||
|
||||
|
||||
async def update_dy_aweme_video(aweme_id, video_content, extension_file_name):
|
||||
"""
|
||||
更新抖音短视频
|
||||
Args:
|
||||
aweme_id:
|
||||
video_content:
|
||||
extension_file_name:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
await DouYinVideo().store_video({"aweme_id": aweme_id, "video_content": video_content, "extension_file_name": extension_file_name})
|
||||
@@ -1,324 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : relakkes@gmail.com
|
||||
# @Time : 2024/1/14 18:46
|
||||
# @Desc : 抖音存储实现类
|
||||
import asyncio
|
||||
import csv
|
||||
import json
|
||||
import os
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
|
||||
import config
|
||||
from base.base_crawler import AbstractStore
|
||||
from tools import utils, words
|
||||
from var import crawler_type_var
|
||||
|
||||
|
||||
def calculate_number_of_files(file_store_path: str) -> int:
|
||||
"""计算数据保存文件的前部分排序数字，支持每次运行代码不写到同一个文件中
|
||||
Args:
|
||||
file_store_path;
|
||||
Returns:
|
||||
file nums
|
||||
"""
|
||||
if not os.path.exists(file_store_path):
|
||||
return 1
|
||||
try:
|
||||
return max([int(file_name.split("_")[0]) for file_name in os.listdir(file_store_path)]) + 1
|
||||
except ValueError:
|
||||
return 1
|
||||
|
||||
|
||||
class DouyinCsvStoreImplement(AbstractStore):
|
||||
csv_store_path: str = "data/douyin"
|
||||
file_count: int = calculate_number_of_files(csv_store_path)
|
||||
|
||||
def make_save_file_name(self, store_type: str) -> str:
|
||||
"""
|
||||
make save file name by store type
|
||||
Args:
|
||||
store_type: contents or comments
|
||||
|
||||
Returns: eg: data/douyin/search_comments_20240114.csv ...
|
||||
|
||||
"""
|
||||
return f"{self.csv_store_path}/{self.file_count}_{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.csv"
|
||||
|
||||
async def save_data_to_csv(self, save_item: Dict, store_type: str):
|
||||
"""
|
||||
Below is a simple way to save it in CSV format.
|
||||
Args:
|
||||
save_item: save content dict info
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns: no returns
|
||||
|
||||
"""
|
||||
pathlib.Path(self.csv_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name = self.make_save_file_name(store_type=store_type)
|
||||
async with aiofiles.open(save_file_name, mode='a+', encoding="utf-8-sig", newline="") as f:
|
||||
writer = csv.writer(f)
|
||||
if await f.tell() == 0:
|
||||
await writer.writerow(save_item.keys())
|
||||
await writer.writerow(save_item.values())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Douyin content CSV storage implementation
|
||||
Args:
|
||||
content_item: note item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=content_item, store_type="contents")
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Douyin comment CSV storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=comment_item, store_type="comments")
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Douyin creator CSV storage implementation
|
||||
Args:
|
||||
creator: creator item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=creator, store_type="creator")
|
||||
|
||||
|
||||
class DouyinDbStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Douyin content DB storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .douyin_store_sql import (add_new_content,
|
||||
query_content_by_content_id,
|
||||
update_content_by_content_id)
|
||||
aweme_id = content_item.get("aweme_id")
|
||||
aweme_detail: Dict = await query_content_by_content_id(content_id=aweme_id)
|
||||
if not aweme_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
if content_item.get("title"):
|
||||
await add_new_content(content_item)
|
||||
else:
|
||||
await update_content_by_content_id(aweme_id, content_item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Douyin content DB storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .douyin_store_sql import (add_new_comment,
|
||||
query_comment_by_comment_id,
|
||||
update_comment_by_comment_id)
|
||||
comment_id = comment_item.get("comment_id")
|
||||
comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_comment(comment_item)
|
||||
else:
|
||||
await update_comment_by_comment_id(comment_id, comment_item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Douyin content DB storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .douyin_store_sql import (add_new_creator,
|
||||
query_creator_by_user_id,
|
||||
update_creator_by_user_id)
|
||||
user_id = creator.get("user_id")
|
||||
user_detail: Dict = await query_creator_by_user_id(user_id)
|
||||
if not user_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_creator(creator)
|
||||
else:
|
||||
await update_creator_by_user_id(user_id, creator)
|
||||
|
||||
class DouyinJsonStoreImplement(AbstractStore):
|
||||
json_store_path: str = "data/douyin/json"
|
||||
words_store_path: str = "data/douyin/words"
|
||||
|
||||
lock = asyncio.Lock()
|
||||
file_count: int = calculate_number_of_files(json_store_path)
|
||||
WordCloud = words.AsyncWordCloudGenerator()
|
||||
|
||||
def make_save_file_name(self, store_type: str) -> (str,str):
|
||||
"""
|
||||
make save file name by store type
|
||||
Args:
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
return (
|
||||
f"{self.json_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.json",
|
||||
f"{self.words_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}"
|
||||
)
|
||||
async def save_data_to_json(self, save_item: Dict, store_type: str):
|
||||
"""
|
||||
Below is a simple way to save it in json format.
|
||||
Args:
|
||||
save_item: save content dict info
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
pathlib.Path(self.json_store_path).mkdir(parents=True, exist_ok=True)
|
||||
pathlib.Path(self.words_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name,words_file_name_prefix = self.make_save_file_name(store_type=store_type)
|
||||
save_data = []
|
||||
|
||||
async with self.lock:
|
||||
if os.path.exists(save_file_name):
|
||||
async with aiofiles.open(save_file_name, 'r', encoding='utf-8') as file:
|
||||
save_data = json.loads(await file.read())
|
||||
|
||||
save_data.append(save_item)
|
||||
async with aiofiles.open(save_file_name, 'w', encoding='utf-8') as file:
|
||||
await file.write(json.dumps(save_data, ensure_ascii=False, indent=4))
|
||||
|
||||
if config.ENABLE_GET_COMMENTS and config.ENABLE_GET_WORDCLOUD:
|
||||
try:
|
||||
await self.WordCloud.generate_word_frequency_and_cloud(save_data, words_file_name_prefix)
|
||||
except:
|
||||
pass
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
content JSON storage implementation
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(content_item, "contents")
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
comment JSON storage implementation
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(comment_item, "comments")
|
||||
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Douyin creator CSV storage implementation
|
||||
Args:
|
||||
creator: creator item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(save_item=creator, store_type="creator")
|
||||
|
||||
|
||||
class DouyinSqliteStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Douyin content SQLite storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .douyin_store_sql import (add_new_content,
|
||||
query_content_by_content_id,
|
||||
update_content_by_content_id)
|
||||
aweme_id = content_item.get("aweme_id")
|
||||
aweme_detail: Dict = await query_content_by_content_id(content_id=aweme_id)
|
||||
if not aweme_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
if content_item.get("title"):
|
||||
await add_new_content(content_item)
|
||||
else:
|
||||
await update_content_by_content_id(aweme_id, content_item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Douyin comment SQLite storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .douyin_store_sql import (add_new_comment,
|
||||
query_comment_by_comment_id,
|
||||
update_comment_by_comment_id)
|
||||
comment_id = comment_item.get("comment_id")
|
||||
comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_comment(comment_item)
|
||||
else:
|
||||
await update_comment_by_comment_id(comment_id, comment_item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Douyin creator SQLite storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .douyin_store_sql import (add_new_creator,
|
||||
query_creator_by_user_id,
|
||||
update_creator_by_user_id)
|
||||
user_id = creator.get("user_id")
|
||||
user_detail: Dict = await query_creator_by_user_id(user_id)
|
||||
if not user_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_creator(creator)
|
||||
else:
|
||||
await update_creator_by_user_id(user_id, creator)
|
||||
@@ -1,111 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
|
||||
from base.base_crawler import AbstractStoreImage, AbstractStoreVideo
|
||||
from tools import utils
|
||||
|
||||
|
||||
class DouYinImage(AbstractStoreImage):
|
||||
image_store_path: str = "data/douyin/images"
|
||||
|
||||
async def store_image(self, image_content_item: Dict):
|
||||
"""
|
||||
store content
|
||||
|
||||
Args:
|
||||
image_content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_image(image_content_item.get("aweme_id"), image_content_item.get("pic_content"), image_content_item.get("extension_file_name"))
|
||||
|
||||
def make_save_file_name(self, aweme_id: str, extension_file_name: str) -> str:
|
||||
"""
|
||||
make save file name by store type
|
||||
|
||||
Args:
|
||||
aweme_id: aweme id
|
||||
extension_file_name: image filename with extension
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
return f"{self.image_store_path}/{aweme_id}/{extension_file_name}"
|
||||
|
||||
async def save_image(self, aweme_id: str, pic_content: str, extension_file_name):
|
||||
"""
|
||||
save image to local
|
||||
|
||||
Args:
|
||||
aweme_id: aweme id
|
||||
pic_content: image content
|
||||
extension_file_name: image filename with extension
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
pathlib.Path(self.image_store_path + "/" + aweme_id).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name = self.make_save_file_name(aweme_id, extension_file_name)
|
||||
async with aiofiles.open(save_file_name, 'wb') as f:
|
||||
await f.write(pic_content)
|
||||
utils.logger.info(f"[DouYinImageStoreImplement.save_image] save image {save_file_name} success ...")
|
||||
|
||||
|
||||
class DouYinVideo(AbstractStoreVideo):
|
||||
video_store_path: str = "data/douyin/videos"
|
||||
|
||||
async def store_video(self, video_content_item: Dict):
|
||||
"""
|
||||
store content
|
||||
|
||||
Args:
|
||||
video_content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_video(video_content_item.get("aweme_id"), video_content_item.get("video_content"), video_content_item.get("extension_file_name"))
|
||||
|
||||
def make_save_file_name(self, aweme_id: str, extension_file_name: str) -> str:
|
||||
"""
|
||||
make save file name by store type
|
||||
|
||||
Args:
|
||||
aweme_id: aweme id
|
||||
extension_file_name: video filename with extension
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
return f"{self.video_store_path}/{aweme_id}/{extension_file_name}"
|
||||
|
||||
async def save_video(self, aweme_id: str, video_content: str, extension_file_name):
|
||||
"""
|
||||
save video to local
|
||||
|
||||
Args:
|
||||
aweme_id: aweme id
|
||||
video_content: video content
|
||||
extension_file_name: video filename with extension
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
pathlib.Path(self.video_store_path + "/" + aweme_id).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name = self.make_save_file_name(aweme_id, extension_file_name)
|
||||
async with aiofiles.open(save_file_name, 'wb') as f:
|
||||
await f.write(video_content)
|
||||
utils.logger.info(f"[DouYinVideoStoreImplement.save_video] save video {save_file_name} success ...")
|
||||
@@ -1,160 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : relakkes@gmail.com
|
||||
# @Time : 2024/4/6 15:30
|
||||
# @Desc : sql接口集合
|
||||
|
||||
from typing import Dict, List, Union
|
||||
|
||||
from async_db import AsyncMysqlDB
|
||||
from async_sqlite_db import AsyncSqliteDB
|
||||
from var import media_crawler_db_var
|
||||
|
||||
|
||||
async def query_content_by_content_id(content_id: str) -> Dict:
|
||||
"""
|
||||
查询一条内容记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from douyin_aweme where aweme_id = '{content_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_content(content_item: Dict) -> int:
|
||||
"""
|
||||
新增一条内容记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("douyin_aweme", content_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_content_by_content_id(content_id: str, content_item: Dict) -> int:
|
||||
"""
|
||||
更新一条记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_id:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("douyin_aweme", content_item, "aweme_id", content_id)
|
||||
return effect_row
|
||||
|
||||
|
||||
|
||||
async def query_comment_by_comment_id(comment_id: str) -> Dict:
|
||||
"""
|
||||
查询一条评论内容
|
||||
Args:
|
||||
comment_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from douyin_aweme_comment where comment_id = '{comment_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_comment(comment_item: Dict) -> int:
|
||||
"""
|
||||
新增一条评论记录
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("douyin_aweme_comment", comment_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_comment_by_comment_id(comment_id: str, comment_item: Dict) -> int:
|
||||
"""
|
||||
更新增一条评论记录
|
||||
Args:
|
||||
comment_id:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("douyin_aweme_comment", comment_item, "comment_id", comment_id)
|
||||
return effect_row
|
||||
|
||||
|
||||
async def query_creator_by_user_id(user_id: str) -> Dict:
|
||||
"""
|
||||
查询一条创作者记录
|
||||
Args:
|
||||
user_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from dy_creator where user_id = '{user_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_creator(creator_item: Dict) -> int:
|
||||
"""
|
||||
新增一条创作者信息
|
||||
Args:
|
||||
creator_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("dy_creator", creator_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_creator_by_user_id(user_id: str, creator_item: Dict) -> int:
|
||||
"""
|
||||
更新一条创作者信息
|
||||
Args:
|
||||
user_id:
|
||||
creator_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("dy_creator", creator_item, "user_id", user_id)
|
||||
return effect_row
|
||||
Reference in New Issue
Block a user