scrapy 下载图片及存储信息
Posted
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了scrapy 下载图片及存储信息相关的知识，希望对你有一定的参考价值。
例1：scrapy项目的使用(利用item收集抓取的返回值)
1、创建scrapy项目
scrapy startproject booklist New Scrapy project 'booklist', using template directory '/usr/local/lib/python3.6/site-packages/scrapy/templates/project', created in: /Users/yuanjicai/booklist You can start your first spider with: cd booklist scrapy genspider example example.com
2、定义要抓取内容的字段(用于回收抓取的数据)
cat booklist/items.py # -*- coding: utf-8 -*- # Define here the models for your scraped items # # See documentation in: # http://doc.scrapy.org/en/latest/topics/items.html import scrapy class BooklistItem(scrapy.Item): # define the fields for your item here like: # name = scrapy.Field() name = scrapy.Field() author = scrapy.Field() publisher = scrapy.Field() editor_date = scrapy.Field() description = scrapy.Field()
3、编写spider进行抓取
cat booklist/spiders/bookspider.py
import scrapy
from booklist.items import BooklistItem
class BookSpider(scrapy.Spider):
name = 'booklist'
start_urls = ['http://www.chinavalue.net/BookInfo/BookList.aspx?page=1']
def parse(self,response):
yield scrapy.Request(response.urljoin("?page=1"),callback=self.parse_page)
for item in response.xpath('//div[@id="ctl00_ContentPlaceHolder1_pagerBook"]/a/@href').extract():
fullurl=response.urljoin(item)
yield scrapy.Request(fullurl,callback=self.parse_page)
def parse_page(self,response):
for item in response.xpath('//div[@id="divBookList"]/div/div[2]/a[1]'):
detail_url=response.urljoin(item.xpath('@href').extract()[0])
yield scrapy.Request(detail_url,callback=self.parse_bookdetail)
def parse_bookdetail(self,response):
bookinfo=BooklistItem()
basic_info=response.xpath('//*[@id="Container"]/div[6]/div[1]/div[2]/div[1]/div[2]')
bookinfo['name']=basic_info.xpath('div[1]/text()').extract()[0].strip()
bookinfo['author']=basic_info.xpath('div[2]/text()').extract()[0].strip()
bookinfo['publisher']=basic_info.xpath('div[3]/text()').extract()[0].strip()
bookinfo['editor_date']=basic_info.xpath('div[4]/text()').extract()[0].strip()
bookinfo['description']=response.xpath('//*[@id="ctl00_ContentPlaceHolder1_pnlIntroBook"]/div[2]/text()').extract()[0].strip()
yield bookinfoparse函数中的“for循环”处理“下一页”的link(下图所示)
parse_page函数负责解析每一页书单中 各item 标题的link(如下图所示)
parse_bookdetail 负责解析每本书的详细属性及内容(如下图所示)
4、运行项目
scrapy crawl booklist -o book-info.csv
上例中将抓取的信息通过yield返回给item中的各字段，然后再通过 output 选项 存储到 book-info.csv 文件中。
例2：scrapy下载图片，并将抓取信息存储到指定位置(文件、mysql、mongodb)
创建项目(下载图片)：
bogon:scrapy yuanjicai$ scrapy startproject bookinfo bogon:douban_booklist yuanjicai$ cd bookinfo/
cat bookinfo/items.py #在item中定义抓取的各字段名，并定义image_urls、image_paths
# -*- coding: utf-8 -*- # Define here the models for your scraped items # # See documentation in: # http://doc.scrapy.org/en/latest/topics/items.html import scrapy class BookinfoItem(scrapy.Item): # define the fields for your item here like: # name = scrapy.Field() name = scrapy.Field() author = scrapy.Field() publisher = scrapy.Field() price = scrapy.Field() rating = scrapy.Field() editor_date = scrapy.Field() images = scrapy.Field() image_urls = scrapy.Field() image_paths = scrapy.Field()
vim bookinfo/settings.py #通过settings指定抓取时使用的header、agent、pipeline、图片或文件保存的位置、img过期时间、mysql用户名/密码/端口、mongo用户名/密码/端口
grep -E -v '^(#|$)' bookinfo/settings.py
BOT_NAME = 'bookinfo'
SPIDER_MODULES = ['bookinfo.spiders']
NEWSPIDER_MODULE = 'bookinfo.spiders'
ROBOTSTXT_OBEY = True
#from faker import Factory
#f = Factory.create()
#USER_AGENT = f.user_agent()
DEFAULT_REQUEST_HEADERS = {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
'Connection': 'keep-alive',
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.75 Safari/537.36',
}
ITEM_PIPELINES = {
#'bookinfo.pipelines.BookinfoStoreMysqlPipeline': 200,
#'bookinfo.pipelines.BookinfoStoreFilePipeline': 200,
'bookinfo.pipelines.BookinfoStoreMongoPipeline': 200,
'bookinfo.pipelines.BookImgsDLPipeline': 300,
}
IMAGES_STORE = '/Users/yuanjicai/Downloads/bookinfo'
IMAGES_EXPIRES = 90
#IMAGES_MIN_HEIGHT = 100
#IMAGES_MIN_WIDTH = 100
#IMAGES_THUMBS = {
# 'small': (50, 50),
# 'big': (270, 270),
#}
MYSQL_HOST = '10.18.101.104'
MYSQL_DBNAME = 'book'
MYSQL_USER = 'root'
MYSQL_PASSWD = '123'
MYSQL_PORT = 3306
MONGODB_HOST = '10.18.101.104'
MONGODB_PORT = 27017
MONGODB_DB = 'book'
MONGODB_COLLECTION = 'bookinfo'（1）爬取一个Item，将图片的URLs放入image_urls字段
（2）从Spider返回的Item，传递到Item Pipeline
（3）当Item传递到ImagePipeline，将调用Scrapy 调度器和下载器完成image_urls中的url的调度和下载。ImagePipeline会自动高优先级抓取这些url，于此同时，item会被锁定直到图片抓取完毕才被解锁。
（4）图片下载成功结束后，图片下载路径、url和校验和等信息会被填充到images字段中。
cat bookinfo/spiders/bookinfo_spider.py #实现抓取内容
# -*- coding: utf-8 -*-
import scrapy
import re
from bookinfo.items import BookinfoItem
class bookinfoSpider(scrapy.Spider):
name = "bookinfo"
start_urls = [ "https://book.douban.com/top250" ]
def parse(self,response):
yield scrapy.Request(response.url,callback=self.parse_page)
for page_url in response.xpath('//div[@class="paginator"]/a/@href').extract():
yield scrapy.Request(page_url,callback=self.parse_page)
def parse_page(self,response):
for item in response.xpath('//div[@class="article"]/div[1]/table/tr[1]'):
bookinfo=BookinfoItem() #在for循环内实例化在item中定义的各字段，抓取每个item使用一个新的bookinfo空间，相互不影响
bookinfo['name']=item.xpath("td[2]/div[1]/a/text()").extract()[0].strip()
bookinfo['price']=item.xpath("td[2]/p/text()").extract()[0].strip().split("/")[-1]
bookinfo['editor_date']=item.xpath("td[2]/p/text()").extract()[0].strip().split("/")[-2]
bookinfo['publisher']=item.xpath("td[2]/p/text()").extract()[0].strip().split("/")[-3]
bookinfo['author']=item.xpath("td[2]/p/text()").extract()[0].strip().split("/")[-4]
bookinfo['rating']=item.xpath("td[2]/div[2]/span[2]/text()").extract()[0]
bookinfo['image_urls']=item.xpath("td[1]/a/img/@src").extract_first()
yield bookinfo
cat bookinfo/pipelines.py #由pipeline中定义的类、方法保存抓取的信息及图片
# -*- coding: utf-8 -*-
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
from scrapy.pipelines.images import ImagesPipeline
from scrapy.exceptions import DropItem
from scrapy.conf import settings #导入settings 是为了在pipeline中调用setting中定义的各DB参数
import scrapy
import codecs
import json
import pymysql
import pymongo
#通过以下pipeline使用pymysql连接并写入mysql server
class BookinfoStoreMysqlPipeline(object):
def __init__(self):
pass
def dbHandle(self):
conn = pymysql.connect(host='10.18.101.104', db='book', user='root', passwd='123', charset='utf8')
return conn
def process_item(self,item,spider):
conn=self.dbHandle()
cursor=conn.cursor()
insert_sql = 'insert into bookinfo(name,author,publisher,url) VALUES (%s,%s,%s,%s)'
try:
cursor.execute(insert_sql,(item["name"],item["author"],item["publisher"],item["image_urls"]))
conn.commit()
except:
conn.rollback()
conn.close()
return item
def spider_close(self,spider):
pass
#通过以下pipeline使用json.dumps形式将返回的数据写入指定json文件中
class BookinfoStoreFilePipeline(object):
def __init__(self):
self.file=codecs.open('bookinfo.json','w',encoding='utf-8')
def process_item(self,item,spider):
line = json.dumps(dict(item),ensure_ascii=False) + "\n"
self.file.write(line)
return item
def spider_colse(self,spider):
self.file.close()
#通过以下pipeline使用pymongo形式将返回的数据写入mongodb中
class BookinfoStoreMongoPipeline(object):
def __init__(self):
conn=pymongo.MongoClient(settings['MONGODB_HOST'],settings['MONGODB_PORT'])
db=conn[settings['MONGODB_DB']]
self.collection = db[settings['MONGODB_COLLECTION']]
def process_item(self,item,spider):
self.collection.insert(dict(item))
return item
def spider_colse(self,spider):
conn.close()
#通过以下pipeline下载抓取过程中存储在image_urls字段的图片
class BookImgsDLPipeline(ImagesPipeline):
default_headers = {
'accept': 'image/webp,image/*,*/*;q=0.8',
'accept-encoding': 'gzip, deflate, sdch, br',
'accept-language': 'zh-CN,zh;q=0.8,en;q=0.6',
'referer': 'https://book.douban.com/top250/',
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36',
}
def get_media_requests(self,item,info):
self.default_headers['referer'] = item['image_urls']
yield scrapy.Request(item['image_urls'], headers=self.default_headers, meta={'bookname':item['name']})
#将每个bookname附加在meta中传递给下一个函数处理
def file_path(self,request,response=None,info=None):
bookname=request.meta['bookname']
image_guid = bookname+'_'+request.url.split('/')[-1] #自定义保存图片的名称
filename = 'full/%s' % (image_guid)
return filename
def item_completed(self,results,item,info):
image_paths = [ value['path'] for ok, value in results if ok ]
if not image_paths:
raise DropItem("Item contains no images")
item['image_paths'] = image_paths[0]
item['images'] = [ value for ok, value in results if ok ]
return item说明：result字典值的格式如下所示：
[(True, {'url': 'https://img3.doubanio.com/mpic/s26012674.jpg', 'path': 'full/b8700497fc0014c87e085747c89476e12162c518.jpg', 'checksum': '4da0defa1ec30229ce724d691f694ad1'})]
Pipline 下载图片时，必须是一个继承ImagesPipeline父类的 类 ，该类必须在setting中调用 ；
ImagePipeline
需要在自定义的ImagePipeline类中重载的方法有：get_media_requests(item, info)和item_completed(results, items, info)
正如工作流程所示，Pipeline将从item中获取图片的URLs并下载它们，所以必须重载get_media_requests，并返回一个Request对象，这些请求对象将被Pipeline处理，当完成下载后，结果将发送到item_completed方法，这些结果为一个二元组的list，每个元祖的包含(success, image_info_or_failure)。 success: boolean值，true表示成功下载 ；如果success=true，image_info_or_error词典包含以下键值对：
url：原始URL
path：本地存储路径
checksum：校验码
以上是关于scrapy 下载图片及存储信息的主要内容，如果未能解决你的问题，请参考以下文章
Scrapy基础————图片下载后将本地路径添加到Item中