从0到1爬虫学习笔记：05Scrapy实战项目

1 手机APP抓包爬虫

（1）item.py

class DouyuspiderItem(scrapy.Item):
    name = scrapy.Field()# 存储照片的名字
    imagesUrls = scrapy.Field()# 照片的url路径
    imagesPath = scrapy.Field()# 照片保存在本地的路径

（2）spiders/douyu.py

import scrapy
import json
from douyuSpider.items import DouyuspiderItem

class DouyuSpider(scrapy.Spider):
    name = "douyu"
    allowd_domains = ["http://capi.douyucdn.cn"]

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

  def parse(self, response):
      # 返回从json里获取 data段数据集合
      data = json.loads(response.text)["data"]

      for each in data:
          item = DouyuspiderItem()
          item["name"] = each["nickname"]
          item["imagesUrls"] = each["vertical_src"]

          yield item

      self.offset += 20
      yield scrapy.Request(self.url + str(self.offset), callback = self.parse)

（3）设置setting.py

ITEM_PIPELINES = {
   'douyuSpider.pipelines.ImagesPipeline': 1}

# Images 的存放位置，之后会在pipelines.py里调用
IMAGES_STORE = "/Users/Power/lesson_python/douyuSpider/Images"

# user-agent
USER_AGENT = 'DYZB/2.290 (iPhone; iOS 9.3.4; Scale/2.00)'

（4）pipelines.py

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

class ImagesPipeline(ImagesPipeline):
    IMAGES_STORE = get_project_settings().get("IMAGES_STORE")

    def get_media_requests(self, item, info):
        image_url