使用Scrapy爬取斗鱼图片

1.具体文件结构

2.代码：

items

# -*- coding: utf-8 -*-

# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html

import scrapy


class DouyuItem(scrapy.Item):
    # define the fields for your item here like:
    nickname = scrapy.Field()
    imagelink = scrapy.Field()
    imagePath = scrapy.Field()
    #pass

douyumeinv

# -*- coding: utf-8 -*-
import scrapy
from douyu.items import DouyuItem
import json


class DouyumeinvSpider(scrapy.Spider):
    #爬虫名
    name = "douyumeinv"
    #表示允许爬虫爬的网站
    allowed_domains = ["capi.douyucdn.cn"]

    #拼接请求链接
    offset = 0
    url = "http://capi.douyucdn.cn/api/v1/getVerticalRoom?limit=20&offset="
    start_urls = [url + str(offset)]

    def parse(self, response):
        # 把json格式的数据转换为python格式，data段是列表
        data = json.loads(response.text)["data"]
        #遍历数据获取值
        for each in data:
            item = DouyuItem()
            item["nickname"] = each["nickname"]
            item["imagelink"] = each["vertical_src"]
            yield item

        #获取下一页的数据
        self.offset += 20
        yield scrapy.Request(self.url + str(self.offset), callback = self.parse)

pipelines

# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html

import scrapy
import os
from scrapy.utils.project import get_project_settings
from scrapy.pipelines.images import ImagesPipeline

class DouyuPipeline(ImagesPipeline):
    # def process_item(self, item, spider):
    #     return item
    #设置图片保存路径
    IMAGES_STORE = get_project_settings().get("IMAGES_STORE")

    def get_media_requests(self, item, info):
        #获取图片链接
        image_url = item["imagelink"]
        #发送图片链接请求
        yield scrapy.Request(image_url)

    def item_completed(self, result, item, info):
        image_path = [x["path"] for ok, x in result if ok]
        #更改文件名
        os.rename(self.IMAGES_STORE + "/" + image_path[0], self.IMAGES_STORE + "/" + item["nickname"] + ".jpg")
        #更爱图片路径名
        item["imagePath"] = self.IMAGES_STORE + "/" + item["nickname"]
        return item

settings

# -*- 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:
#
#     http://doc.scrapy.org/en/latest/topics/settings.html
#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'douyu'

SPIDER_MODULES = ['douyu.spiders']
NEWSPIDER_MODULE = 'douyu.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'douyu (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = True

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.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 = {
  "User-Agent" : "DYZB/1 CFNetwork/808.2.16 Darwin/16.3.0"
  # 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
  # 'Accept-Language': 'en',
}

# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'douyu.middlewares.DouyuSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'douyu.middlewares.MyCustomDownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'douyu.pipelines.DouyuPipeline': 300,
}
IMAGES_STORE = "Images"
# Enable and configure the AutoThrottle extension (disabled by default)
# See http://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 http://scrapy.readthedocs.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'

启动：

cd 到项目目录

scrapy crawl 爬虫名

结果：