Spaces:
Paused
Paused
File size: 8,598 Bytes
842e08e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 |
# 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 16:58
# @Desc : 小红书存储实现类
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 XhsCsvStoreImplement(AbstractStore):
csv_store_path: str = "data/xhs"
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/xhs/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:
f.fileno()
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):
"""
Xiaohongshu 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):
"""
Xiaohongshu 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):
"""
Xiaohongshu content CSV storage implementation
Args:
creator: creator dict
Returns:
"""
await self.save_data_to_csv(save_item=creator, store_type="creator")
class XhsDbStoreImplement(AbstractStore):
async def store_content(self, content_item: Dict):
"""
Xiaohongshu content DB storage implementation
Args:
content_item: content item dict
Returns:
"""
from .xhs_store_sql import (add_new_content,
query_content_by_content_id,
update_content_by_content_id)
note_id = content_item.get("note_id")
note_detail: Dict = await query_content_by_content_id(content_id=note_id)
if not note_detail:
content_item["add_ts"] = utils.get_current_timestamp()
await add_new_content(content_item)
else:
await update_content_by_content_id(note_id, content_item=content_item)
async def store_comment(self, comment_item: Dict):
"""
Xiaohongshu content DB storage implementation
Args:
comment_item: comment item dict
Returns:
"""
from .xhs_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):
"""
Xiaohongshu content DB storage implementation
Args:
creator: creator dict
Returns:
"""
from .xhs_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 XhsJsonStoreImplement(AbstractStore):
json_store_path: str = "data/xhs/json"
words_store_path: str = "data/xhs/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):
"""
Xiaohongshu content JSON storage implementation
Args:
creator: creator dict
Returns:
"""
await self.save_data_to_json(creator, "creator")
|