无法使用 skimage 通过 url 读取图像

如何解决无法使用 skimage 通过 url 读取图像

我抓取了一些图像链接并尝试使用 skimage 读取它并将它们转换为字符串，但失败了。这是我的代码：

import requests

from lxml import etree

from skimage import io

import pytesseract

pytesseract.pytesseract.tesseract_cmd = 'C:/Program Files/Tesseract-OCR/tesseract.exe'

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML,like Gecko) Chrome/87.0.4280.88 Safari/537.36','Cookie': 'antipas=3J5894C659Y4128mb084uM86; uuid=acee566c-264c-40f6-8b67-ef6708e60a35; ganji_uuid=9480781269465181883490; clueSourceCode=%2A%2300; sessionid=f03f9416-5158-4fe5-d3fd-5cf697aebf73; lg=1; cainfo=%7B%22ca_a%22%3A%22-%22%2C%22ca_b%22%3A%22-%22%2C%22ca_s%22%3A%22seo_google%22%2C%22ca_n%22%3A%22default%22%2C%22ca_medium%22%3A%22-%22%2C%22ca_term%22%3A%22-%22%2C%22ca_content%22%3A%22-%22%2C%22ca_campaign%22%3A%22-%22%2C%22ca_kw%22%3A%22-%22%2C%22ca_i%22%3A%22-%22%2C%22scode%22%3A%22-%22%2C%22keyword%22%3A%22-%22%2C%22ca_keywordid%22%3A%22-%22%2C%22display_finance_flag%22%3A%22-%22%2C%22platform%22%3A%221%22%2C%22version%22%3A1%2C%22client_ab%22%3A%22-%22%2C%22guid%22%3A%22acee566c-264c-40f6-8b67-ef6708e60a35%22%2C%22ca_city%22%3A%22bj%22%2C%22sessionid%22%3A%22f03f9416-5158-4fe5-d3fd-5cf697aebf73%22%7D; close_finance_popup=2021-01-28; _gl_tracker=%7B%22ca_source%22%3A%22-%22%2C%22ca_name%22%3A%22-%22%2C%22ca_kw%22%3A%22-%22%2C%22ca_id%22%3A%22-%22%2C%22ca_s%22%3A%22self%22%2C%22ca_n%22%3A%22-%22%2C%22ca_i%22%3A%22-%22%2C%22sid%22%3A63162699730%7D; cityDomain=gz; user_city_id=16; preTime=%7B%22last%22%3A1611873323%2C%22this%22%3A1611180370%2C%22pre%22%3A1611180370%7D'
}


# Get detail from url function:
def get_detail_urls(url):
    rsp = requests.get(url,headers=headers)
    text = rsp.content.decode('utf-8')
    html = etree.HTML(text)
    ul = html.xpath('//ul[@class="carlist clearfix js-top"]')[0]
    lis = ul.xpath('./li')
    detail_urls = []
    for i in lis:
        detail_url = i.xpath('./a/@href')
        detail_url = 'https://www.guazi.com' + detail_url[0]
        detail_urls.append(detail_url)
    return detail_urls


# First URL
url = 'https://www.guazi.com/gz/01'

# Parse Data
detail_urls = get_detail_urls(url)
for detail_url in detail_urls:
    resp = requests.get(detail_url,headers=headers)
    text = resp.content.decode('utf-8')
    html = etree.HTML(text)
    imges = html.xpath('//li[@class="one"]//img[@*]')[0]
    imges = etree.tostring(time).decode('utf-8')
    imges = time.split(" ")[1].split("=")[1].replace('',"")
    image = io.imread(imeges)
    print(pytesseract.image_to_string(image))

当我运行上面的代码时：

Traceback (most recent call last): File "C:/Users/naive/Extract_Data/GuaZi.py",line 46,in <module>
image = io.imread(time) File "C:\Users\naive\AppData\Local\Programs\Python\Python38-32\lib\site-packages\skimage\io\_io.py",line 48,in imread
img = call_plugin('imread',fname,plugin=plugin,**plugin_args)File "C:\Users\naive\AppData\Local\Programs\Python\Python38-32\lib\site-packages\skimage\io\manage_plugins.py",line 207,in call_plugin
return func(*args,**kwargs)File "C:\Users\naive\AppData\Local\Programs\Python\Python38-32\lib\site-packages\skimage\io\_plugins\imageio_plugin.py",line 10,in imread
return np.asarray(imageio_imread(*args,**kwargs))File "C:\Users\naive\AppData\Local\Programs\Python\Python38-32\lib\site-packages\imageio\core\functions.py",line 265,in imread
reader = read(uri,format,"i",**kwargs)File "C:\Users\naive\AppData\Local\Programs\Python\Python38-32\lib\site-packages\imageio\core\functions.py",line 172,in get_reader
request = Request(uri,"r" + mode,**kwargs)File "C:\Users\naive\AppData\Local\Programs\Python\Python38-32\lib\site-packages\imageio\core\request.py",line 124,in __init__
self._parse_uri(uri)File "C:\Users\naive\AppData\Local\Programs\Python\Python38-32\lib\site-packages\imageio\core\request.py",line 260,in _parse_uri
raise FileNotFoundError("No such file: '%s'" % fn)FileNotFoundError: No such file: 'C:\Users\naive\Extract_Data\"https:\image1.guazistatic.com\qn200416174108c46443da16f09fbdb5460e27e065e319.jpg"'

我打印了我抓取的所有链接并将链接放入 io.imread() 并且它工作正常。不知道为什么我用直接抓取的链接就不行了。