qnloft
/
MediaCrawler
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat: 小红书增加指定帖子爬取功能 

fix: 修复程序一些异常 bug
refactor: 优化部分代码逻辑
This commit is contained in:
Relakkes 2023-11-18 13:38:11 +08:00
parent f24c892471
commit 700946b28a
9 changed files with 102 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
README.md
View File

@ -16,15 +16,21 @@
- [x] 小红书登录（二维码、手机号、cookies）
- [x] 小红书Sign请求签名
- [x] 小红书指定关键词爬去
- [x] 小红书指定帖子爬去
- [x] 抖音Sign请求签名
- [x] 代理池实现（手机号+IP）
- [x] 并发执行爬虫请求
- [x] 抖音登录（二维码、手机号、cookies）
- [x] 抖音滑块（模拟滑动实现，准确率不太OK）
- [x] 抖音指定关键爬取
- [x] 支持登录成功后的上下文浏览器环境保留
- [x] 代理池实现（手机号+IP）
- [x] 并发执行爬虫请求
- [x] 数据保存到CSV中（默认）
- [x] 数据保持到数据库中（可选）
## 待实现
- [ ] 抖音指定帖子爬取
- [ ] 快手爬虫实现
## 使用方法
@ -51,13 +57,31 @@
4. 运行爬虫程序
```shell
python main.py --platform xhs --lt qrcode
# 从配置文件中读取关键词搜索相关的帖子并爬去帖子信息与评论
python main.py --platform xhs --lt qrcode --type search
# 从配置文件中读取指定的帖子ID列表获取指定帖子的信息与评论信息
python main.py --platform xhs --lt qrcode --type detail
```
5. 打开对应APP扫二维码登录
6. 等待爬虫程序执行完毕，数据会保存到 `data/xhs` 目录下
## 常见程序运行出错问题
```shell
# Q: 爬去抖音报错: `execjs._exceptions.ProgramError: SyntaxError: 缺少 ';'`
# A: 该错误为缺少 nodejs 环境这个错误安装 nodejs 环境即可，版本为：`v16.8.0`
# Q: 可以指定关键词爬取吗？
# A: 在config/base_config.py 中 KEYWORDS 参数用于控制需要爬去的关键词
# Q: 可以指定帖子爬去吗？
# A：在config/base_config.py 中 SPECIFIED_ID_LIST 参数用于控制需要指定爬去的帖子ID列表
# Q: 刚开始能爬取数据，过一段时间就是失效了？
# A：出现这种情况多半是由于你的账号触发了平台风控机制了，❗️❗️请勿大规模对平台进行爬虫，影响平台。
```
## 项目代码结构

2
base/base_crawler.py
View File

@ -5,7 +5,7 @@ from base.proxy_account_pool import AccountPool
class AbstractCrawler(ABC):
@abstractmethod
def init_config(self, platform: str, login_type: str, account_pool: AccountPool):
def init_config(self, platform: str, login_type: str, account_pool: AccountPool, crawler_type: str):
pass
@abstractmethod

9
config/base_config.py
View File

@ -3,6 +3,7 @@ PLATFORM = "xhs"
KEYWORDS = "python,golang"
LOGIN_TYPE = "qrcode" # qrcode or phone or cookie
COOKIES = "" # login by cookie, if login_type is cookie, you must set this value
CRAWLER_TYPE = "search"
# enable ip proxy
ENABLE_IP_PROXY = False
@ -24,3 +25,11 @@ CRAWLER_MAX_NOTES_COUNT = 20
# max concurrency num
MAX_CONCURRENCY_NUM = 10
# specified note id list
SPECIFIED_ID_LIST = [
"6422c2750000000027000d88",
"64ca1b73000000000b028dd2",
"630d5b85000000001203ab41",
]

7
main.py
View File

@ -23,11 +23,13 @@ class CrawlerFactory:
async def main():
# define command line params ...
parser = argparse.ArgumentParser(description='Media crawler program.')
parser.add_argument('--platform', type=str, help='Media platform select (xhs|dy)', choices=["xhs", "dy"],
parser.add_argument('--platform', type=str, help='Media platform select (xhs | dy)', choices=["xhs", "dy"],
default=config.PLATFORM)
parser.add_argument('--lt', type=str, help='Login type (qrcode | phone | cookie)',
choices=["qrcode", "phone", "cookie"], default=config.LOGIN_TYPE)
parser.add_argument('--type', type=str, help='crawler type (search | detail)',
choices=["search","detail"],default=config.CRAWLER_TYPE)
# init account pool
account_pool = proxy_account_pool.create_account_pool()
@ -40,7 +42,8 @@ async def main():
crawler.init_config(
platform=args.platform,
login_type=args.lt,
account_pool=account_pool
account_pool=account_pool,
crawler_type=args.type
)
await crawler.start()

17
media_platform/douyin/core.py
View File

@ -21,6 +21,7 @@ from .login import DouYinLogin
class DouYinCrawler(AbstractCrawler):
platform: str
login_type: str
crawler_type: str
context_page: Page
dy_client: DOUYINClient
account_pool: AccountPool
@ -30,10 +31,11 @@ class DouYinCrawler(AbstractCrawler):
self.user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36" # fixed
self.index_url = "https://www.douyin.com"
def init_config(self, platform: str, login_type: str, account_pool: AccountPool) -> None:
def init_config(self, platform: str, login_type: str, account_pool: AccountPool, crawler_type: str) -> None:
self.platform = platform
self.login_type = login_type
self.account_pool = account_pool
self.crawler_type = crawler_type
async def start(self) -> None:
account_phone, playwright_proxy, httpx_proxy = self.create_proxy_info()
@ -63,8 +65,12 @@ class DouYinCrawler(AbstractCrawler):
await login_obj.begin()
await self.dy_client.update_cookies(browser_context=self.browser_context)
# search_posts
if self.crawler_type == "search":
# Search for notes and retrieve their comment information.
await self.search()
elif self.crawler_type == "detail":
# Get the information and comments of the specified post
await self.get_specified_notes()
utils.logger.info("Douyin Crawler finished ...")
@ -74,7 +80,7 @@ class DouYinCrawler(AbstractCrawler):
request_keyword_var.set(keyword)
utils.logger.info(f"Current keyword: {keyword}")
aweme_list: List[str] = []
dy_limit_count = 10 # douyin fixed limit page 10
dy_limit_count = 10
page = 0
while (page + 1) * dy_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:
try:
@ -95,6 +101,11 @@ class DouYinCrawler(AbstractCrawler):
utils.logger.info(f"keyword:{keyword}, aweme_list:{aweme_list}")
await self.batch_get_note_comments(aweme_list)
async def get_specified_notes(self):
"""Get the information and comments of the specified post"""
# todo douyin support
pass
async def batch_get_note_comments(self, aweme_list: List[str]) -> None:
task_list: List[Task] = []
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)

32
media_platform/xhs/core.py
View File

@ -12,7 +12,7 @@ from base.base_crawler import AbstractCrawler
from base.proxy_account_pool import AccountPool
from models import xiaohongshu as xhs_model
from tools import utils
from var import request_keyword_var
from var import crawler_type_var
from .client import XHSClient
from .exception import DataFetchError
@ -22,6 +22,7 @@ from .login import XHSLogin
class XiaoHongShuCrawler(AbstractCrawler):
platform: str
login_type: str
crawler_type: str
context_page: Page
xhs_client: XHSClient
account_pool: AccountPool
@ -31,10 +32,11 @@ class XiaoHongShuCrawler(AbstractCrawler):
self.index_url = "https://www.xiaohongshu.com"
self.user_agent = utils.get_user_agent()
def init_config(self, platform: str, login_type: str, account_pool: AccountPool) -> None:
def init_config(self, platform: str, login_type: str, account_pool: AccountPool, crawler_type: str) -> None:
self.platform = platform
self.login_type = login_type
self.account_pool = account_pool
self.crawler_type =crawler_type
async def start(self) -> None:
account_phone, playwright_proxy, httpx_proxy = self.create_proxy_info()
@ -72,8 +74,16 @@ class XiaoHongShuCrawler(AbstractCrawler):
await login_obj.begin()
await self.xhs_client.update_cookies(browser_context=self.browser_context)
if self.crawler_type == "search":
# Search for notes and retrieve their comment information.
crawler_type_var.set("search")
await self.search()
elif self.crawler_type == "detail":
# Get the information and comments of the specified post
crawler_type_var.set("detail")
await self.get_specified_notes()
else:
pass
utils.logger.info("Xhs Crawler finished ...")
@ -82,8 +92,6 @@ class XiaoHongShuCrawler(AbstractCrawler):
utils.logger.info("Begin search xiaohongshu keywords")
xhs_limit_count = 20 # xhs limit page fixed value
for keyword in config.KEYWORDS.split(","):
# set keyword to context var
request_keyword_var.set(keyword)
utils.logger.info(f"Current search keyword: {keyword}")
page = 1
while page * xhs_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:
@ -107,6 +115,19 @@ class XiaoHongShuCrawler(AbstractCrawler):
utils.logger.info(f"Note details: {note_details}")
await self.batch_get_note_comments(note_id_list)
async def get_specified_notes(self):
"""Get the information and comments of the specified post"""
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list = [
self.get_note_detail(note_id=note_id, semaphore=semaphore) for note_id in config.SPECIFIED_ID_LIST
]
note_details = await asyncio.gather(*task_list)
for note_detail in note_details:
if note_detail is not None:
await xhs_model.update_xhs_note(note_detail)
await self.batch_get_note_comments(config.SPECIFIED_ID_LIST)
async def get_note_detail(self, note_id: str, semaphore: asyncio.Semaphore) -> Optional[Dict]:
"""Get note detail"""
async with semaphore:
@ -115,6 +136,9 @@ class XiaoHongShuCrawler(AbstractCrawler):
except DataFetchError as ex:
utils.logger.error(f"Get note detail error: {ex}")
return None
except KeyError as ex:
utils.logger.error(f"have not fund note detail note_id:{note_id}, err: {ex}")
return None
async def batch_get_note_comments(self, note_list: List[str]):
"""Batch get note comments"""

10
models/xiaohongshu.py
View File

@ -8,7 +8,7 @@ from tortoise.models import Model
import config
from tools import utils
from var import request_keyword_var
from var import crawler_type_var
class XhsBaseModel(Model):
@ -101,9 +101,9 @@ async def update_xhs_note(note_item: Dict):
await XHSNote.filter(note_id=note_id).update(**note_data.dict())
else:
# Below is a simple way to save it in CSV format.
source_keywords = request_keyword_var.get()
pathlib.Path(f"data/xhs").mkdir(parents=True, exist_ok=True)
with open(f"data/xhs/notes_{source_keywords}.csv", mode='a+', encoding="utf-8-sig", newline="") as f:
save_file_name = f"data/xhs/{crawler_type_var.get()}_notes_{utils.get_current_date()}.csv"
with open(save_file_name, mode='a+', encoding="utf-8-sig", newline="") as f:
writer = csv.writer(f)
if f.tell() == 0:
writer.writerow(local_db_item.keys())
@ -141,9 +141,9 @@ async def update_xhs_note_comment(note_id: str, comment_item: Dict):
await XHSNoteComment.filter(comment_id=comment_id).update(**comment_data.dict())
else:
# Below is a simple way to save it in CSV format.
source_keywords = request_keyword_var.get()
pathlib.Path(f"data/xhs").mkdir(parents=True, exist_ok=True)
with open(f"data/xhs/comment_{source_keywords}.csv", mode='a+', encoding="utf-8-sig", newline="") as f:
save_file_name = f"data/xhs/{crawler_type_var.get()}_comment_{utils.get_current_date()}.csv"
with open(save_file_name, mode='a+', encoding="utf-8-sig", newline="") as f:
writer = csv.writer(f)
if f.tell() == 0:
writer.writerow(local_db_item.keys())

9
tools/utils.py
View File

@ -267,3 +267,12 @@ def get_tracks(distance: int, level: str = "easy") -> List[int]:
from . import easing
_, tricks = easing.get_tracks(distance, seconds=2, ease_func="ease_out_expo")
return tricks
def get_current_time():
ISOTIMEFORMAT = '%Y-%m-%d %X'
return tme.strftime(ISOTIMEFORMAT, time.localtime())
def get_current_date():
ISOTIMEFORMAT = '%Y-%m-%d'
return time.strftime(ISOTIMEFORMAT, time.localtime())

1
var.py
View File

@ -1,3 +1,4 @@
from contextvars import ContextVar
request_keyword_var: ContextVar[str] = ContextVar("request_keyword", default="")
crawler_type_var: ContextVar[str] = ContextVar("crawler_type", default="")