# -*- coding: utf-8 -*-
import scrapy
from pyquery import PyQuery
from scrapy.http import Request
from ..items import XiaohuarItem
class XiaohuaSpider(scrapy.Spider):
name = 'xiaohua'
allowed_domains = ['xiaohuar.com']
start_urls = ['http://www.xiaohuar.com/hua/']
visited_page = set()
def parse(self, response):
pq = PyQuery(response.text)
urls = pq.find("#page .page_num a")
for url in urls.items():#网页
index_page = url.attr("href")
if index_page not in self.visited_page and index_page != None:
self.visited_page.add(index_page)
yield Request(url=index_page, callback=self.parse)
items = pq.find("#list_img .item_list .item")
for item in items.items():#获得所需的标签内容
title = item.find(".img img").attr("alt")
name = item.find(".price").text()
img_src = item.find(".img a img").attr("src")
if "http://www.xiaohuar.com" not in img_src:
img_src = "http://www.xiaohuar.com%s" % img_src
yield XiaohuarItem(title=title, name=name, img_src=img_src)
piplines.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 requests
class XiaohuarPipeline(object):
def process_item(self, item, spider):
print(item["title"],item["name"],item["img_src"])
pic_name = " ".join([item["title"],item["name"]]) + ".jpg"
img_data = requests.get(item["img_src"])
with open(pic_name,"wb") as f:
f.write(img_data.content)
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 XiaohuarItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
title = scrapy.Field()
name = scrapy.Field()
img_src = scrapy.Field()
settings.py
# -*- coding: utf-8 -*-
# Scrapy settings for xiaohuar 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 = 'xiaohuar'
SPIDER_MODULES = ['xiaohuar.spiders']
NEWSPIDER_MODULE = 'xiaohuar.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'xiaohuar (+http://www.yourdomain.com)'
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.62 Safari/537.36'
# 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 = {
# 'xiaohuar.middlewares.XiaohuarSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'xiaohuar.middlewares.XiaohuarDownloaderMiddleware': 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 = {
'xiaohuar.pipelines.XiaohuarPipeline': 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'
DEPTH_LIMIT = 1