scrapy爬取图片详细步骤

407次阅读
没有评论

1.爬取https://image.so.com/z?ch=photography图片,用谷歌浏览器打开开发者工具,选中XHR选项, 由于使用了AJAX ,可以看到页面的刷新情况. 待会附上的源码就有拼接url:https://image.so.com/zj?key=value&key1=value2…
以及json字段解析

scrapy爬取图片详细步骤

scrapy爬取图片详细步骤
scrapy爬取图片详细步骤
1 . images.py 源码

import scrapy from urllib.parse import urlencode from scrapy import Spider,Request import json from images360.items import Images360Item class ImagesSpider(scrapy.Spider): name = 'images' allowed_domains = ['images.so.com'] start_urls = ['http://images.so.com/'] def parse(self, response): result = json.loads(response.text) for image in result.get('list'): item = Images360Item() item['id'] = image.get('id') item['url'] = image.get('qhimg_url') item['title'] = image.get('group_title') item['thumb'] = image.get('qhimg_thumb') yield item

def start_requests(self): data = {'ch': 'photography', 'listtype': 'new', 'temp': '1'} base_url = 'https://image.so.com/zj?' for page in range(1,self.settings.get('MAX_PAGE') + 1): #由于页面是ajax请求,sn号,每页30 data['sn'] = (page-1)*30 #拼接成ch=photography&sn=30&listtype=new&temp=1 params = urlencode(data) #拼接完整的url url = base_url + params print(url) print('\n') yield Request(url = url,callback = self.parse)

2 . items.py源码如下:

import scrapy class Images360Item(scrapy.Item): collection = table = 'images' id = scrapy.Field() url = scrapy.Field() title = scrapy.Field() thumb = scrapy.Field()

3 . pipelines.py 源码:

import pymongo import pymysql from scrapy.pipelines.images import ImagesPipeline from scrapy import Request from scrapy.exceptions import DropItem #通过mongo存储的类 class MongoPipeline(object): """docstring for MongoPipeline""" def __init__(self, mongo_uri,mongo_db): self.mongo_uri = mongo_uri self.mongo_db = mongo_db @classmethod def from_crawler(cls, crawler): return cls( mongo_uri = crawler.settings.get('MONGO_URI'), mongo_db = crawler.settings.get('MONGO_DB') ) def open_spider(self,spider): self.client = pymongo.MongoClient(self.mongo_uri) #如果self.mongo_db数据库不存在,则自动创建 self.db = self.client[self.mongo_db] def process_item(self,item,spider): #如果结合item.collection不存在,则自动创建 self.db[item.collection].insert(dict(item)) return item # 必须实现返回 def close_spider(self,spider): self.client.close()

#通过mysql存储的类 class MysqlPipeline(object): def __init__(self, host, database, user, password, port,sql_image): self.host = host self.database = database self.user = user self.password = password self.port = port self.sql_image = sql_image @classmethod def from_crawler(cls, crawler): return cls( host = crawler.settings.get('MYSQL_HOST'), database = crawler.settings.get('MYSQL_DATABASE'), user = crawler.settings.get('MYSQL_USER'), password = crawler.settings.get('MYSQL_PASSWORD'), port = crawler.settings.get('MYSQL_PORT'), sql_image = crawler.settings.get('SQL_IMAGE') ) def open_spider(self,spider): self.db = pymysql.connect(self.host, self.user, self.password, self.database, charset='utf8', port=self.port) self.cursor = self.db.cursor() #创建表/字段语句,一定要先创建,后面才能执行insert动作 self.cursor.execute(self.sql_image) def process_item(self,item,spider): data = dict(item) keys = ','.join(data.keys()) # print('keys:%s'%keys) values = ', '.join(['%s']*len(data)) # print('values:%s'%values) sql = 'insert into %s (%s) values(%s)' % (item.table, keys, values) self.cursor.execute(sql,tuple(data.values())) self.db.commit() return item def close_spider(self,spider): self.db.close()

#保存到本地类 class Images360Pipeline(ImagesPipeline): def file_path(self, request, response=None, info=None): # 重命名,若不重写这函数,图片名为哈希,就是一串乱七八糟的名字 image_guid = request.url.split('/')[-1] # 提取url前面名称作为图片名。 return image_guid def item_completed(self, results, item, info): images_paths = [x['path'] for ok, x in results if ok] if not images_paths: raise DropItem('Image Download Failed') return item def get_media_requests(self, item, info): yield Request(item['url']) ```

4 . settings.py源码如下:

import random # user agent 列表 USER_AGENT_LIST = [ "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)", "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)", "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)", "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)", "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)", "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)", "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6", "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1", "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0", "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5", "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20", "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER", "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)", "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)", "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1", "Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5", "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre", "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11", "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36" ] #随机生成user agent USER_AGENT = random.choice(USER_AGENT_LIST) BOT_NAME = 'images360' SPIDER_MODULES = ['images360.spiders'] NEWSPIDER_MODULE = 'images360.spiders' #Obey robots.txt rules ROBOTSTXT_OBEY = False ITEM_PIPELINES = { 'images360.pipelines.MysqlPipeline': 300, 'images360.pipelines.MongoPipeline': 301, 'images360.pipelines.Images360Pipeline': 302, } #定义爬取的页数 MAX_PAGE = 20 #定义mongodb数据库 MONGO_URI = 'localhost' MONGO_DB = 'images360'

#定义mysql数据库 MYSQL_HOST = 'localhost' MYSQL_DATABASE = 'images360' MYSQL_USER = 'root' MYSQL_PASSWORD = '123456' MYSQL_PORT = 3306 IMAGES_STORE = './images' #创建表/各个字段信息 SQL_IMAGE = '''create table if not exists images( id varchar(100) not null, url varchar(100) not null, title varchar(100) not null, thumb varchar(100) null ) '''

运行之后结果如下:
scrapy爬取图片详细步骤
scrapy爬取图片详细步骤

神龙|纯净稳定代理IP免费测试>>>>>>>>天启|企业级代理IP免费测试>>>>>>>>IPIPGO|全球住宅代理IP免费测试

相关文章:

版权声明:Python教程2022-10-28发表,共计8475字。
新手QQ群:570568346,欢迎进群讨论 Python51学习