first commit

Comics/items.py

@@ -0,0 +1,27 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class ComicsItem(scrapy.Item):
+    #漫画名
+    name = scrapy.Field()
+    #链接
+    link = scrapy.Field()
+
+class ComicItem(scrapy.Item):
+    name = scrapy.Field()
+    chapter = scrapy.Field()
+    list_img = scrapy.Field()
+    author= scrapy.Field()
+    icon = scrapy.Field()
+    tags = scrapy.Field()
+    dep = scrapy.Field()
+    date = scrapy.Field()
+    chapters = scrapy.Field()
+    chapter_href= scrapy.Field()
+    genre = scrapy.Field()
+    age_rating = scrapy.Field()

Comics/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 ComicsSpiderMiddleware:
+    # 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 ComicsDownloaderMiddleware:
+    # 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)

Comics/pipelines.py

@@ -0,0 +1,41 @@
+# 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
+from itemadapter import ItemAdapter
+
+
+class ComicsPipeline:
+    def open_spider(self,spider):
+        self.fp = open('book.json','w',encoding='utf-8')
+
+    def comic_process(self,images):
+        count = 1
+        scramble_count = 0
+        (files_name,images_url) = [[],[]]
+        for image in images:
+            (image_src,scramble) = [image.get("src"),image.get("scramble")]
+            count_image = "{:0>3d}".format(count)
+            image_src_suffix = "."+str(image_src).split(".")[-1]
+            image_file_name = count_image+image_src_suffix
+            if scramble:
+                de_str = str(image_src).split("/")[-1].replace(image_src_suffix,"==")
+                #blocks_num = imageUtils.encodeImage(de_str)
+                #image_file_name = ComicPath.getFileScrambleImageName(count=count_image,block=blocks_num,suffix=image_src_suffix)
+                scramble_count += 1
+            files_name.append(image_file_name)
+            images_url.append(image_src)
+            #downUtils.putDownImageUrlDirFile(image_src,ComicPath.getDirComicChapter(),image_file_name)
+            count+=1
+            
+    # item就是yield后面的对象
+    def process_item(self, item, spider):   
+        self.fp.write(str(item))
+        self.comic_process(item["list_img"])
+        return item
+
+    def close_spider(self,spider):
+        self.fp.close()

Comics/settings.py

@@ -0,0 +1,88 @@
+# Scrapy settings for Comics 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 = 'Comics'
+
+SPIDER_MODULES = ['Comics.spiders']
+NEWSPIDER_MODULE = 'Comics.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'Comics (+http://www.yourdomain.com)'
+USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.182 Safari/537.36'
+# 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 = {
+#    'Comics.middlewares.ComicsSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'Comics.middlewares.ComicsDownloaderMiddleware': 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 = {
+    'Comics.pipelines.ComicsPipeline': 300,
+}
+
+# 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'

Comics/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.

Comics/spiders/rm_comic.py

@@ -0,0 +1,44 @@
+import scrapy,json
+from Comics.items import ComicItem
+from Comics.spiders.utils.CommonUtils import CommonUtils
+
+class RmComicSpider(scrapy.Spider):
+    name = 'rm_comic'
+    allowed_domains = ['rm01.xyz']
+    main_url = 'https://rm01.xyz'
+    #start_urls = ['https://rm01.xyz/books/63b65185-f798-4c8f-a0b0-8811615908fd/0']
+    
+    def start_requests(self):
+        yield scrapy.Request(self.main_url + '/books/63b65185-f798-4c8f-a0b0-8811615908fd', callback=self.parse_comic)
+    
+    def parse_comic(self, response):
+        comic = ComicItem()
+        comic['name'] = response.xpath('//div[@class="col"]/h5/text()').extract_first()
+        comic['icon'] = response.xpath('//img[@class="img-thumbnail"]/@src').extract_first()
+        comic['author'] = response.xpath('//div[contains(@class,"bookid_bookInfo")]/p[1]/text()').extract()[1]
+        comic['tags'] = response.xpath('//div[contains(@class,"bookid_bookInfo")]/p[3]/b/text()').extract_first()
+        comic['dep'] = response.xpath('//div[contains(@class,"bookid_bookInfo")]/p[4]/text()').extract()[1]
+        comic['date'] = response.xpath('//div[contains(@class,"bookid_bookInfo")]/p[5]/small/text()').extract()[1]
+        comic['chapters'] = response.xpath('//div[contains(@class,"bookid_chapterBox")]//div[contains(@class,"bookid_chapter")]/a/text()').extract()
+        comic['chapter_href'] = response.xpath('//div[contains(@class,"bookid_chapterBox")]//div[contains(@class,"bookid_chapter")]/a/@href').extract()
+        list_img = []
+        for link in comic['chapter_href']:
+            list_img.append(scrapy.Request(self.main_url+link, callback=self.parse_chapter,errback=self.err))
+        comic['list_img'] = list_img
+        yield comic
+    
+    def err(self):
+        print("Error=====")
+        
+    def parse_chapter(self, response):
+        data = response.xpath('//script[@id="__NEXT_DATA__"]/text()').extract_first()
+        str_exec="props.pageProps."
+        comic_name = CommonUtils.parseExec(data,str_exec+"bookName")
+        chapterName = CommonUtils.parseExec(data,str_exec+"chapterName")
+        description = CommonUtils.parseExec(data,str_exec+"description")
+        images = CommonUtils.parseExec(data,str_exec+"images")
+        chapter_api_url = CommonUtils.parseExec(data,str_exec+"chapterAPIPath")
+        yield ComicItem(name=comic_name,chapter=chapterName,dep=description,list_img=images)
+    
+    def parse(self, response):
+        raise NotImplementedError

Comics/spiders/utils/CommonUtils.py

@@ -0,0 +1,11 @@
+import json
+
+class CommonUtils:
+    @classmethod
+    def parseExec(cls,data,exec):
+        if data !=None and exec != None:
+            dots = str(exec).split(".")
+            if not isinstance(data,dict): data = json.loads(data)
+            for dot in dots:
+                data = data.get(dot)
+        return data

run.py

@@ -0,0 +1,5 @@
+# -*- coding: utf-8 -*-
+
+from scrapy import cmdline
+
+cmdline.execute("scrapy crawl rm_comic".split())

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 = Comics.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = Comics