抓图片下载如何使用自定义文件名
||
对于我的项目，我目前正在使用ImagesPipeline。下载的图像以其URL的SHA1哈希作为文件名存储。
如何使用我自己的自定义文件名存储文件？
如果我的自定义文件名需要包含同一项目中的另一个抓取字段，该怎么办？例如使用
item[\'desc\']
没有找到相关结果
已邀请:
6 个回复
旗低饶彤
class FSImagesStoreChangeableDirectory(FSImagesStore): def persist_image(self, key, image, buf, info,append_path): absolute_path = self._get_filesystem_path(append_path+\'/\'+key) self._mkdir(os.path.dirname(absolute_path), info) image.save(absolute_path) class ProjectPipeline(ImagesPipeline): def __init__(self): super(ImagesPipeline, self).__init__() store_uri = settings.IMAGES_STORE if not store_uri: raise NotConfigured self.store = FSImagesStoreChangeableDirectory(store_uri)蜂佬渺
class MyImagesPipeline(ImagesPipeline): #Name download version def file_path(self, request, response=None, info=None): #item=request.meta[\'item\'] # Like this you can use all from item, not just url. image_guid = request.url.split(\'/\')[-1] return \'full/%s\' % (image_guid) #Name thumbnail version def thumb_path(self, request, thumb_id, response=None, info=None): image_guid = thumb_id + response.url.split(\'/\')[-1] return \'thumbs/%s/%s.jpg\' % (thumb_id, image_guid) def get_media_requests(self, item, info): #yield Request(item[\'images\']) # Adding meta. Dunno how to put it in one line :-) for image in item[\'images\']: yield Request(image)亥套惟间连
class MyImagesPipeline(ImagesPipeline): #Name download version def image_key(self, url): image_guid = url.split(\'/\')[-1] return \'full/%s.jpg\' % (image_guid) #Name thumbnail version def thumb_key(self, url, thumb_id): image_guid = thumb_id + url.split(\'/\')[-1] return \'thumbs/%s/%s.jpg\' % (thumb_id, image_guid) def get_media_requests(self, item, info): yield Request(item[\'images\'])伞腹
def file_path(self, request, response=None, info=None): return request.meta.get(\'filename\',\'\') def get_media_requests(self, item, info): img_url = item[\'img_url\'] meta = {\'filename\': item[\'name\']} yield Request(url=img_url, meta=meta)中将您想要的名称添加到Request meta中，然后在中将其取回。寿柬窟年
import os import json img_dir = os.path.join(os.getcwd(), \'images\\\\full\') item_dir = os.path.join(os.getcwd(), \'data.json\') with open(item_dir, \'r\') as item_json: items = json.load(item_json) for item in items: if len(item[\'images\']) > 0: cur_file = item[\'images\'][0][\'path\'].split(\'/\')[-1] cur_format = cur_file.split(\'.\')[-1] new_title = item[\'title\']+\'.%s\'%cur_format file_path = os.path.join(img_dir, cur_file) os.rename(file_path, os.path.join(img_dir, new_title))告耸
class MyImagesPipeline(ImagesPipeline): #Name download version def file_path(self, request, response=None, info=None): #item=request.meta[\'item\'] # Like this you can use all from item, not just url. image_guid = request.url.split(\'/\')[-1] return \'full/%s\' % (image_guid) #Name thumbnail version def thumb_path(self, request, thumb_id, response=None, info=None): image_guid = thumb_id + request.url.split(\'/\')[-1] return \'thumbs/%s/%s.jpg\' % (thumb_id, image_guid) def get_media_requests(self, item, info): #yield Request(item[\'images\']) # Adding meta. Dunno how to put it in one line :-) for image in item[\'images\']: yield Request(image)