网站:
切换到摄影界面。
打开开发者工具:
我们在下拉的时候可以看到这是一个ajax请求,数据结构是json。
sn=30返回的是前30张图片,sn=60返回的是30到60的图片。
创建项目:
构造请求:
url为:http://images.so.com/zj?ch=photography&listtype=new&sn=30&listtype=new
def start_requests(self): data = {'ch': 'photography', 'listtype': 'new'} base_url = 'http://images.so.com/zj?' for page in range(1,self.settings.get('MAX_PAGE')+1): data['sn'] = page*30 data['temp'] = 1 params = urlencode(data) url = base_url+params yield Request(url, self.parse)
提取信息:
首先要定义一个Item:
from scrapy import Item,Field class Images360Item(Item): #MongoDb存储的collection名称和mysql的表名称 collection = table = 'images' id = Field() url = Field() title = Field() thumb = Field()
提取Spider的信息:
from ..items import Images360Item import json
def parse(self, response): # print(response) result = json.loads(response.text) for image in result.get('list'): item = Images360Item() item['id'] = image.get('imageid') item['url'] = image.get('qhimg_url') item['title'] = image.get('group_title') item['thumb'] = image.get('qhimg_thumb_url') yield item
存储信息
pipelines.py文件中
Mongo存储
class MongoPipeline(object): #初始化数据库 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): """初始化数据库""" self.client = pymongo.MongoClient(self.mongo_uri) self.db = self.client[self.mongo_db] def process_item(self,item,spider): """存入数据""" self.db[item.collection].insert(dict(item)) return item def close(self,item,spider): """关闭数据库""" self.client.close()
Mysql存储:
class MysqlPipeline(): def __init__(self, host, database, user, password, port): self.host = host self.database = database self.user = user self.password = password self.port = port @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'), ) 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() def close_spider(self, spider): self.db.close() def process_item(self, item, spider): data = dict(item) keys = ', '.join(data.keys()) values = ', '.join(['%s'] * len(data)) sql = 'insert into %s (%s) values (%s)' % (item.table, keys, values) self.cursor.execute(sql, tuple(data.values())) self.db.commit() return item
然后下载图片,代码如下:
class ImagePipeline(ImagesPipeline): def file_path(self, request, response=None, info=None): # 获取下载路径 url = request.url print('******************') print(url) # 命名 file_name = url.split('/')[-1] return file_name def item_completed(self, results, item, info): # results对应下载结果,是一个列表形式 image_paths = [x['path'] for ok, x in results if ok] if not image_paths: raise DropItem('Image Downloaded Failed') return item def get_media_requests(self, item, info): #将url字段拿出来,执行下载。 yield Request(item['url'])
然后在settings.py文件中添加下载路径:
IMAGES_STORE = './images'
启用管道文件:
ITEM_PIPELINES = { 'images360.pipelines.ImagePipeline': 300, 'images360.pipelines.MongoPipeline': 301, 'images360.pipelines.MysqlPipeline': 302, }
数据库配置的设置:
MONGO_URI = 'localhost' MONGO_DB = 'images360' MYSQL_HOST = 'localhost' MYSQL_DATABASE = 'images360' MYSQL_PORT = 3306 MYSQL_USER = 'root' MYSQL_PASSWORD = '123456'
最后保存的结果如下:
Mongo:
Mysql:
注意:最后几项的配置一定不能出错,不然或是产生存储不了的结果,或是图片无法下载的结果。