Upload 12 files

danbooru_cawler/.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+pics/
+*.pyc
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

danbooru_cawler/README.md

@@ -0,0 +1,32 @@
+# danbooru_cawler 
+一个基于scrapy的danbooru图片抓取工具
+
+## 运行
+
+初次运行需要安装环境
+
+```
+python -m venv venv
+.\venv\Scripts\activate
+python -m pip install --upgrade pip
+pip install -r requirements.txt
+```
+
+以后每次运行只需要
+
+```
+.\venv\Scripts\activate
+python .\main.py
+```
+
+## 说明
+
+调整需要抓取的tag可以更改/danbooru_crawler/settings.py文件内的SEARCH_TAG值，多个tag用+相连
+
+图片将输出在/pics/full文件夹内
+
+如果运行一段时间后没有图片可能是Pillow版本过低，建议在虚拟环境下执行
+```
+pip uninstall Pillow
+pip install Pillow
+```

danbooru_cawler/danbooru_crawler/items.py

@@ -0,0 +1,18 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class DanbooruCrawlerItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass
+
+
+class ImagedownloadItem(scrapy.Item):
+    image_name = scrapy.Field()
+    image_urls = scrapy.Field()
+    images = scrapy.Field()

danbooru_cawler/danbooru_crawler/middlewares.py

@@ -0,0 +1,103 @@
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+# useful for handling different item types with a single interface
+from itemadapter import is_item, ItemAdapter
+
+
+class DanbooruCrawlerSpiderMiddleware:
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(self, response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(self, response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, or item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(self, response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Request or item objects.
+        pass
+
+    def process_start_requests(self, start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info("Spider opened: %s" % spider.name)
+
+
+class DanbooruCrawlerDownloaderMiddleware:
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the downloader middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_request(self, request, spider):
+        # Called for each request that goes through the downloader
+        # middleware.
+
+        # Must either:
+        # - return None: continue processing this request
+        # - or return a Response object
+        # - or return a Request object
+        # - or raise IgnoreRequest: process_exception() methods of
+        #   installed downloader middleware will be called
+        return None
+
+    def process_response(self, request, response, spider):
+        # Called with the response returned from the downloader.
+
+        # Must either;
+        # - return a Response object
+        # - return a Request object
+        # - or raise IgnoreRequest
+        return response
+
+    def process_exception(self, request, exception, spider):
+        # Called when a download handler or a process_request()
+        # (from other downloader middleware) raises an exception.
+
+        # Must either:
+        # - return None: continue processing this exception
+        # - return a Response object: stops process_exception() chain
+        # - return a Request object: stops process_exception() chain
+        pass
+
+    def spider_opened(self, spider):
+        spider.logger.info("Spider opened: %s" % spider.name)

danbooru_cawler/danbooru_crawler/pipelines.py

@@ -0,0 +1,22 @@
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+# useful for handling different item types with a single interface
+import scrapy
+from itemadapter import ItemAdapter
+from scrapy.exceptions import DropItem
+from scrapy.pipelines.images import ImagesPipeline
+
+
+class DanbooruCrawlerPipeline:
+    def process_item(self, item, spider):
+        return item
+
+
+class PicsDownloadPipeline(ImagesPipeline):
+    def file_path(self, request, response=None, info=None, *, item=None):
+        image_guid = item["image_name"]
+        return f"full/{image_guid}.jpg"

danbooru_cawler/danbooru_crawler/settings.py

@@ -0,0 +1,98 @@
+# Scrapy settings for danbooru_crawler project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     https://docs.scrapy.org/en/latest/topics/settings.html
+#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = "danbooru_crawler"
+SEARCH_TAG = "tsubasa_tsubasa"
+SEARCH_TYPE = 1  # 0 / 1 是否抓取缩略图，0代表抓缩略图，1代表原图
+SEARCH_LINK = False  # True / False 连锁搜索(即搜索子图，训练画风可以打开，训练概念等会出现与tag特征不符的图导致污染训练集)
+
+SPIDER_MODULES = ["danbooru_crawler.spiders"]
+NEWSPIDER_MODULE = "danbooru_crawler.spiders"
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+# USER_AGENT = "danbooru_crawler (+http://www.yourdomain.com)"
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = False
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+# CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+# DOWNLOAD_DELAY = 3
+# The download delay setting will honor only one of:
+# CONCURRENT_REQUESTS_PER_DOMAIN = 16
+# CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+# COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+# TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+# DEFAULT_REQUEST_HEADERS = {
+#    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
+#    "Accept-Language": "en",
+# }
+
+# Enable or disable spider middlewares
+# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+# SPIDER_MIDDLEWARES = {
+#    "danbooru_crawler.middlewares.DanbooruCrawlerSpiderMiddleware": 543,
+# }
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+# DOWNLOADER_MIDDLEWARES = {
+#    "danbooru_crawler.middlewares.DanbooruCrawlerDownloaderMiddleware": 543,
+# }
+
+# Enable or disable extensions
+# See https://docs.scrapy.org/en/latest/topics/extensions.html
+# EXTENSIONS = {
+#    "scrapy.extensions.telnet.TelnetConsole": None,
+# }
+
+# Configure item pipelines
+# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+    "danbooru_crawler.pipelines.PicsDownloadPipeline": 1,
+    # "scrapy.pipelines.PicsDownloadPipeline": 1,
+}
+IMAGES_STORE = "./pics"
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
+# AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+# AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+# AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+# AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+# AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+# HTTPCACHE_ENABLED = True
+# HTTPCACHE_EXPIRATION_SECS = 0
+# HTTPCACHE_DIR = "httpcache"
+# HTTPCACHE_IGNORE_HTTP_CODES = []
+# HTTPCACHE_STORAGE = "scrapy.extensions.httpcache.FilesystemCacheStorage"
+
+# Set settings whose default value is deprecated to a future-proof value
+REQUEST_FINGERPRINTER_IMPLEMENTATION = "2.7"
+TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
+FEED_EXPORT_ENCODING = "utf-8"

danbooru_cawler/danbooru_crawler/spiders/__init__.py

@@ -0,0 +1,4 @@
+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

danbooru_cawler/danbooru_crawler/spiders/danbooru.py

@@ -0,0 +1,58 @@
+import scrapy
+from .. import settings
+from .. import items
+from urllib import parse
+
+
+class DanbooruSpider(scrapy.Spider):
+    # custom_settings = {"DOWNLOAD_DELAY": 0.3, "RANDOMIZE_DOWNLOAD_DELAY": True}
+
+    name = "danbooru"
+    allowed_domains = ["donmai.us"]
+    url = "https://danbooru.donmai.us"
+    start_urls = [f"https://danbooru.donmai.us/posts?tags={settings.SEARCH_TAG}"]
+
+    def parse(self, response):
+        """搜索页"""
+        # 详情页
+        for _ in response.xpath('//a[@class="post-preview-link"]/@href').getall():
+            self.logger.info(f"详情页 {parse.urljoin(self.url, _)}")
+            yield response.follow(_, callback=self.parse_pic_page_url, priority=1)
+        # 下一页
+        next_url = response.xpath('//a[@rel="next" and @href]/@href').get()
+        if next_url is not None:
+            self.logger.info(f"下一页 {parse.urljoin(self.url,next_url)}")
+            yield response.follow(next_url, callback=self.parse, priority=2)
+
+    def parse_pic_page_url(self, response):
+        """详情页"""
+        self.logger.info(f"详情页 {response.url}")
+        img_url = None
+        # 套图
+        if settings.SEARCH_LINK:
+            link_img_url_list = response.xpath(
+                '//div/article[not(contains(@class,"current-post"))]/div/a/@href'
+            ).getall()
+            for _ in link_img_url_list:
+                yield response.follow(_, callback=self.parse_pic_page_url, priority=1)
+
+        # 抓取图片源地址
+        if settings.SEARCH_TYPE == 0:
+            img_url = response.xpath("//section/picture/source/@srcset").get()
+        elif settings.SEARCH_TYPE == 1:
+            img_url = response.xpath(
+                '//li/a[@class="image-view-original-link"]/@href'
+            ).get()
+        if img_url is None:
+            img_url = response.xpath("//section/picture/source/@srcset").get()
+        self.logger.info(f"资源url {img_url}")
+        tags = response.xpath("//@data-tags").get()
+        name = img_url.split("/")[-1].split(".")[0]
+        with open(f"./pics/{name}.txt", "w") as txt_file:
+            tags = tags.split(" ")
+            tags = ",".join(tags)
+            txt_file.write(tags)
+        img_items = items.ImagedownloadItem()
+        img_items["image_urls"] = [img_url]
+        img_items["image_name"] = name
+        yield img_items

danbooru_cawler/main.py

@@ -0,0 +1,7 @@
+from scrapy.cmdline import execute
+import os
+import sys
+
+if __name__ == "__main__":
+    # sys.path.append(os.path.dirname(os.path.abspath(__file__)))
+    execute(["scrapy", "crawl", "danbooru"])

danbooru_cawler/requirements.txt

@@ -0,0 +1,2 @@
+itemadapter==0.8.0
+Scrapy==2.11.0

danbooru_cawler/scrapy.cfg

@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
+
+[settings]
+default = danbooru_crawler.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = danbooru_crawler