版权声明:柠萌 https://blog.csdn.net/Hack_Different/article/details/83867543
一、编辑 items.py 文件
# -*- 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
from scrapy import Field
class JmyspiderItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
image_url = Field()
pass
二、编辑 settings.py 文件
# -*- coding: utf-8 -*-
# Scrapy settings for jmySpider 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 = 'jmySpider'
SPIDER_MODULES = ['jmySpider.spiders']
NEWSPIDER_MODULE = 'jmySpider.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'jmySpider (+http://www.yourdomain.com)'
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
# 修改编码为utf-8
# FEED_EXPORT_ENCODING = 'utf-8'
# 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 = {
# 'jmySpider.middlewares.JmyspiderSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'jmySpider.middlewares.JmyspiderDownloaderMiddleware': 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 = {
'jmySpider.pipelines.JmyspiderPipeline': 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'
三、数据分析
注:可以跳过,进行第四步,先查看结果
1. 分析链接
2. 获取数据链接
将上面的链接放入 jmy.py 文件的 start_urls 中即可
四、创建爬虫文件 jmy.py
# -*- coding: utf-8 -*-
from scrapy.spiders import CrawlSpider
from jmySpider.items import JmyspiderItem
import json
class JmySpider(CrawlSpider):
name = 'jmySpider'
# 设置headers伪装成浏览器
headers = {
'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_3) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.54 Safari/536.5'
}
# 主链接为 http://image.baidu.com/search/index?tn=baiduimage&ps=1&ct=201326592&lm=-1&cl=2&nc=1&ie=utf-8&word=%E9%87%91%E6%9C%A8%E7%A0%94
# ajax 数据链接如下↓
# 初始URL
start_urls = [
'http://image.baidu.com/search/acjson?tn=resultjson_com&ipn=rj&ct=201326592&is=&fp=result&queryWord=%E9%87%91%E6%9C%A8%E7%A0%94&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=&z=&ic=&word=%E9%87%91%E6%9C%A8%E7%A0%94&s=&se=&tab=&width=&height=&face=&istype=&qc=&nc=1&fr=&expermode=&pn=30&rn=30&gsm=1e&1541678883249=',
'http://image.baidu.com/search/acjson?tn=resultjson_com&ipn=rj&ct=201326592&is=&fp=result&queryWord=%E9%87%91%E6%9C%A8%E7%A0%94&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=&z=&ic=&word=%E9%87%91%E6%9C%A8%E7%A0%94&s=&se=&tab=&width=&height=&face=&istype=&qc=&nc=1&fr=&expermode=&pn=60&rn=30&gsm=3c&1541678883388='
]
def parse(self, response):
# 从Json文件内容中提取所有img的内容
imgs = json.loads(response.body)['data']
for eachImage in imgs:
item = JmyspiderItem() # items中的类
try:
item['image_url'] = [eachImage['middleURL']]
yield item
except Exception as e:
print(e)
五、创建 main.py 文件,用于启动爬虫
from scrapy import cmdline
cmdline.execute("scrapy crawl jmySpider -o result.csv".split()) #用命令行启动
运行 main.py 即可