手機App抓包爬蟲
1. items.py
class DouyuspiderItem(scrapy.Item): name = scrapy.Field()# 存儲照片的名字 imagesUrls = scrapy.Field()# 照片的url路徑 imagesPath = scrapy.Field()# 照片保存在本地的路徑 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): # 返回從json里獲取 data段數據集合 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. 設置setting.py
ITEM_PIPELINES = {'douyuSpider.pipelines.ImagesPipeline': 1} # Images 的存放位置，之后會在pipelines.py里調用 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 = item["imagesUrls"] yield scrapy.Request(image_url) def item_completed(self, results, item, info): # 固定寫法，獲取圖片路徑，同時判斷這個路徑是否正確，如果正確，就放到 image_path里，ImagesPipeline源碼剖析可見 image_path = [x["path"] for ok, x in results if ok] os.rename(self.IMAGES_STORE + "/" + image_path[0], self.IMAGES_STORE + "/" + item["name"] + ".jpg") item["imagesPath"] = self.IMAGES_STORE + "/" + item["name"] return item #get_media_requests的作用就是為每一個圖片鏈接生成一個Request對象，這個方法的輸出將作為item_completed的輸入中的results，results是一個元組，每個元組包括(success, imageinfoorfailure)。如果success=true，imageinfoor_failure是一個字典，包括url/path/checksum三個key。 在項目根目錄下新建main.py文件,用於調試
from scrapy import cmdline cmdline.execute('scrapy crawl douyu'.split()) 執行程序
py2 main.py