scrapy爬去图片
scrapy startproject Photo
scrapy genspider Photo 'baidu.com'
代码如下
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 PhtotoItem(scrapy.Item):
# define the fields for your item here like:
nickname = scrapy.Field()
imgurl = scrapy.Field()
Photo.py
# -*- coding: utf-8 -*-
import scrapy
from phtoto.items import PhtotoItem
import json
class PhotoSpider(scrapy.Spider):
name = 'Photo'
# allowed_domains = [''user.qzone.com'']
baseurl = "http://capi.douyucdn.cn/api/v1/getVerticalRoom?limit=20&offset="
offset = 0
start_urls = [baseurl + str(offset)]
def parse(self, response):
data = json.loads(response.body)['data']
if not len(data):
return
for d in data:
item = PhtotoItem()
item['nickname'] = d['nickname']
item['imgurl'] = d['vertical_src']
yield item
# 下载所有
# self.offset += 20
# scrapy.Request(self.baseurl + str(self.offset))
setting.py
# -*- coding: utf-8 -*-
# Scrapy settings for phtoto 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 = 'phtoto'
SPIDER_MODULES = ['phtoto.spiders']
NEWSPIDER_MODULE = 'phtoto.spiders'
IMAGES_STORE = "/Users/Administrator/PycharmProjects/untitled2/phtoto/phtoto/img/"
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'phtoto (+http://www.yourdomain.com)'
# 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://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 = {
# 'phtoto.middlewares.PhtotoSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'phtoto.middlewares.PhtotoDownloaderMiddleware': 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
ITEM_PIPELINES = {
'phtoto.pipelines.PhtotoPipeline': 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'
pipelines.py
# -*- coding: utf-8 -*-
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
import scrapy
import os
from settings import IMAGES_STORE as image_store
from scrapy.pipelines.images import ImagesPipeline
class PhtotoPipeline(ImagesPipeline):
def get_media_requests(self, item, info):
imgurl = item['imgurl']
yield scrapy.Request(imgurl)
# s设置item相关信息 重新设置path和图片名
def item_completed(self, results, item, info):
imgpath = [x['path'] for ok, x in results if ok]
os.rename(image_store + imgpath[0], image_store + item['nickname'] + ".jpg")
return item
目录结构如下