Scrapy爬取搜狗图片

1.新建项目

scrapy startproject images360

scrapy genspider images images.so.com

2.构造请求

在setting.py定义爬取的页数

MAX_PAGE=50

定义start_request()方法，用来生成50次请求

    def start_requests(self):
        data = {'ch': 'photography', 'listtype': 'new'}
        base_url = 'http://image.so.com/zj?'
        for page in range(1, self.settings.get('MAX_PAGE') + 1):
            data['sn'] = page * 30
            params = urlencode(data)
            url = base_url + params
            yield Request(url, self.parse)

再修改setting中ROBOTSTXT_OBEY将其设置为False

3.提取信息

定义ImageItem

from scrapy import Item, Field
class ImageItem(Item):
    collection = table = 'images'
    id = Field()
    url = Field()
    title = Field()
    thumb = Field()

提取Spider的有关信息，将parse()方法改为：

    def parse(self, response):
        result = json.loads(response.text)
        for image in result.get('list'):
            item = ImageItem()
            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

4.Mongo

MONGO_URI = 'localhost'
MONGO_DB = 'images360'

import pymongo


class MongoPipeline(object):
    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_db=crawler.settings.get('MONGO_DB'),
            mongo_uri=crawler.settings.get('MONGO_URI')
        )

    def open_spider(self, spider):
        self.client = pymongo.MongoClient(self.mongo_uri)
        self.db = self.client[self.mongo_db]

    def process_item(self, item, spider):
        self.db[item.collection].insert(dict(item))
        return item

    def close_spider(self, spider):
        self.client.close()

5.Mysql

MYSQL_HOST = '127.0.0.1'
MYSQL_DATABASE = 'images360'
MYSQL_USER = 'root'
MYSQL_PASSWORD = 'qaz123'
MYSQL_PORT = 3306

import pymysql

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

6.存储图片到本地

在setting加入：

IMAGES_STORE='./images'

from scrapy import Request
from scrapy.exceptions import DropItem
from scrapy.pipelines.images import ImagesPipeline


class ImagePipeline(ImagesPipeline):
    def file_path(self, request, response=None, info=None):
        url = request.url
        file_name = url.split('/')[-1]
        return file_name

    def item_completed(self, results, item, info):
        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):
        yield Request(item['url'])

setting

ITEM_PIPELINES = {
    'images360.pipelines.ImagePipeline': 300,
    'images360.pipelines.MongoPipeline': 301,
    'images360.pipelines.MysqlPipeline': 302,
}