1.手机端数据包的抓取(响应教程可自行百度)
2.具体程序编写
items.py
# -*- coding: utf-8 -*- # Define here the models for your scraped items # # See documentation in: # https://doc.scrapy.org/en/latest/topics/items.html import scrapy class DouyuItem(scrapy.Item): # define the fields for your item here like: # 1.主播所在版块 game_name = scrapy.Field() # 2.主播房间号 room_id = scrapy.Field() # 3.主播链接 vertical_src = scrapy.Field() # 4.主播昵称 nickname = scrapy.Field() # 存储照片名称信息5. message = scrapy.Field()
douyu.py
# -*- coding: utf-8 -*- import scrapy import json from Douyu.items import DouyuItem class DouyuSpider(scrapy.Spider): name = 'douyu' allowed_domains = ['douyucdn.cn'] # 0.抓取斗鱼手机端app中颜值分类的数据包 baseURL = "http://capi.douyucdn.cn/api/v1/getVerticalRoom?limit=20&offset=" offset = 0 start_urls = [baseURL+str(offset)] def parse(self, response): # 1.将已经编码的json字符串解码为python对象(此处的Python对象时一个字典) # 1.data键对应的值是一个列表,列表中每一个元素又是一个字典 data_list = json.loads(response.body)["data"] # 2.判断data是否为空(为空终止,不为空继续翻页) if not data_list: return for data in data_list: item = DouyuItem() item["game_name"] = data["game_name"] item["room_id"] = data["room_id"] item["vertical_src"] = data["vertical_src"] item["nickname"] = data["nickname"] item["message"] = data["game_name"]+data["room_id"]+data["nickname"] # 3.返回item对象给管道进行处理 yield item # 4.JSON文件只能通过翻页来爬取,不能通过xpath()提取 self.offset += 20 # 5.将请求发回给引擎,引擎返回给调度器,调度器将请求入队列 yield scrapy.Request(self.baseURL+str(self.offset), callback=self.parse)
pipelines.py
# -*- coding: utf-8 -*- # # Don't forget to add your pipeline to the ITEM_PIPELINES setting # See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html # 1.导入scrapy包中pipelines文件夹下images.py文件中ImagesPipeline类 import os import scrapy from Douyu.settings import IMAGES_STORE as images_store from scrapy.pipelines.images import ImagesPipeline class DouyuPipeline(ImagesPipeline): def get_media_requests(self, item, info): """图片下载""" image_link = item["vertical_src"] # 2.管道将图片链接交给下载器下载 yield scrapy.Request(image_link) def item_completed(self, results, item, info): """图片重命名""" # 3.取出results中图片信息中:图片的存储路径 # results是一个列表,列表中一个元组,元组中两个元素,第二个元素又是一个字典 / md5码 # 推导式写法取值(最外层的列表相当于results列表) img_path = [x["path"] for ok, x in results if ok] # 4.为下载图片重命名 # 4.os.rename(src_name, dst_name) os.rename(images_store+img_path[0], images_store + item["message"]+".jpg") return item
settings.py
# -*- coding: utf-8 -*- # Scrapy settings for Douyu project # # For simplicity, this file contains only settings considered important or # commonly used. You can find more settings consulting the documentation: # # https://doc.scrapy.org/en/latest/topics/settings.html # https://doc.scrapy.org/en/latest/topics/downloader-middleware.html # https://doc.scrapy.org/en/latest/topics/spider-middleware.html BOT_NAME = 'Douyu' SPIDER_MODULES = ['Douyu.spiders'] NEWSPIDER_MODULE = 'Douyu.spiders' # 1.设置保存下载图片的路径images_store # 1.另外一种路径方式IMAGES_STORE = "E:\\Python\\课程代码\\Douyu\\Douyu\\spiders\\" IMAGES_STORE = "E:/Python/课程代码/Douyu/Douyu/spiders/" # Crawl responsibly by identifying yourself (and your website) on the user-agent # 2.配置手机移动端user_agent USER_AGENT = 'Mozilla/5.0 (iPhone 84; CPU iPhone OS 10_3_3 like Mac OS X) AppleWebKit/603.3.8 (KHTML, like Gecko) Version/10.0 MQQBrowser/7.8.0 Mobile/14G60 Safari/8536.25 MttCustomUA/2 QBWebViewType/1 WKType/1' # Obey robots.txt rules # 3.禁用robots协议(设置为False或者直接注释掉) 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://doc.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://doc.scrapy.org/en/latest/topics/spider-middleware.html #SPIDER_MIDDLEWARES = { # 'Douyu.middlewares.DouyuSpiderMiddleware': 543, #} # Enable or disable downloader middlewares # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html #DOWNLOADER_MIDDLEWARES = { # 'Douyu.middlewares.DouyuDownloaderMiddleware': 543, #} # Enable or disable extensions # See https://doc.scrapy.org/en/latest/topics/extensions.html #EXTENSIONS = { # 'scrapy.extensions.telnet.TelnetConsole': None, #} # Configure item pipelines # See https://doc.scrapy.org/en/latest/topics/item-pipeline.html # 4.启用管道文件 ITEM_PIPELINES = { 'Douyu.pipelines.DouyuPipeline': 300, } # Enable and configure the AutoThrottle extension (disabled by default) # See https://doc.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://doc.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'
start.py
# -*- coding:utf-8 -*- from scrapy import cmdline cmdline.execute("scrapy crawl douyu".split())
3.图片爬取结果展示