iCrawler很适合下载图片，但是如何保存源url呢？

Question

iCrawler非常适合下载图片。但是，我想不出如何保存图像源urls来进行归属。我计划用图像制作幻灯片，并将qr代码嵌入到图像中，以便归属。我正在使用进行修改，如下所示：

#!/usr/bin/env python3

from icrawler.builtin import GoogleImageCrawler
import os
import time
import random
from PIL import Image
from PIL.ExifTags import TAGS
import json

wordlist = open("/home/scott/unity-projects/spelling_bee/spelling-game-python-prototype/good_words.txt").read().splitlines()
pausecounter=0
for word in wordlist: 
    
    with open('/home/scott/unity-projects/spelling_bee/spelling-game-python-prototype/data/add.json') as f:
        data = json.load(f)


    example = data[0]["meanings"][0]["definitions"][0]["example"]



    pausecounter = pausecounter + 1;

    pathish="/home/scott/unity-projects/spelling_bee/spelling-game-python-prototype/images/"
    pathish2="/home/scott/unity-projects/spelling_bee/spelling-game-python-prototype/images-compressed/"
    pathish3="/home/scott/unity-projects/spelling_bee/spelling-game-python-prototype/images-videoed/"
    if (os.path.exists(pathish3+word+'.mp4')):
        print("found word: "+word)
        time.sleep(0.033)
        continue
    searchphrase = word+" "+example
    google_Crawler = GoogleImageCrawler(storage = {'root_dir': r'images'})
    google_Crawler.crawl(keyword = searchphrase, max_num = 15, filters = dict(
    license='commercial,modify'))
    
    for number in range(1,16):
        filename=pathish+str.zfill(str(number), 6)
        newfilename=pathish+word+"_"+str.zfill(str(number), 6)
        compressedpath="/home/scott/unity-projects/spelling_bee/spelling-game-python-prototype/images-compressed/"+word+"_"+str.zfill(str(number), 6)+".jpg"
        compressedpathqmp4="/home/scott/unity-projects/spelling_bee/spelling-game-python-prototype/images-videoed/"+word+".mp4"
        print(newfilename)
        print(filename)
        if (os.path.exists(filename+'.jpg')):
            os.rename(filename+'.jpg', newfilename+'.jpg')
            os.system("convert "+newfilename+".jpg -resize 512x512> -compose Copy -gravity center -extent 512x512 -quality 98 "+compressedpath)
        if (os.path.exists(filename+'.png')):
            os.rename(filename+'.png', newfilename+'.png')
            os.system("convert "+newfilename+".png -resize 512x512> -background white -alpha remove -alpha off -compose Copy -gravity center -extent 512x512 -quality 98  "+compressedpath)
    
    os.system("ffmpeg -i images-compressed/"+word+"_%06d.jpg -vf \"scale=512:512,setpts=80*PTS\" -crf 38 -profile:v high -level:v 5.1 -pix_fmt yuv420p "+compressedpathqmp4)
    time.sleep(random.random()*pausecounter)
    if pausecounter > 10:
        pausecounter = 0

对于保存的每个图像，我想将一个包含其源url的文件保存在一个单独的文件中。

Answer 1

我黑了一些文档的例子。我不是蟒蛇专家，所以我无法解释这是如何工作的，但这就是我解决问题的方法。希望您可以跟随变量名称。因为我不确定这是怎么回事，但确实如此。唯一的缺陷是它释放了一个额外的url文件。

#!/usr/bin/env python3

import base64
from icrawler import ImageDownloader
from icrawler.builtin import GoogleImageCrawler
from six.moves.urllib.parse import urlparse

class getAttribution(ImageDownloader):
    def get_filename(self, task, default_ext):
        global word
        url = urlparse(task['file_url'])[0] + "://" +urlparse(task['file_url'])[1] + urlparse(task['file_url'])[2]
        filename = super(getAttribution, self).get_filename(
        task, default_ext)
        print(url +" "+ filename)
        file = open("test-delete/"+word +"_"+ filename+".txt","w")
        file.write(url)
        file.close()
        return word +"_"+ filename

google_crawler = GoogleImageCrawler(
downloader_cls=getAttribution,
downloader_threads=1,
storage={'root_dir': 'test-delete'})

word='sand'`enter code here`

google_crawler.crawl(word, max_num=12, filters = dict(
    license='commercial,modify'))