我有一个文本文件中的 url 列表。我希望将图像下载到特定文件夹,我该怎么做。chrome 或任何其他程序中是否有任何插件可以从 url 下载图像
Create a folder in your machine.
Place your text file of images URL in the folder.
cd
to that folder. Use wget -i images.txt
You will find all your downloaded files in the folder.
This needs to be made into a function with error handling but it repeatedly downloads images for image classification projects
import requests
urls = pd.read_csv('cat_urls.csv') #save the url list as a dataframe
rows = []
for index, i in urls.iterrows():
rows.append(i[-1])
counter = 0
for i in rows:
file_name = 'cat' + str(counter) + '.jpg'
print(file_name)
response = requests.get(i)
file = open(file_name, "wb")
file.write(response.content)
file.close()
counter += 1
import os
import time
import sys
import urllib
from progressbar import ProgressBar
def get_raw_html(url):
version = (3,0)
curr_version = sys.version_info
if curr_version >= version: #If the Current Version of Python is 3.0 or above
import urllib.request #urllib library for Extracting web pages
try:
headers = {}
headers['User-Agent'] = "Mozilla/5.0 (X11; Linux i686) AppleWebKit/537.17 (KHTML, like Gecko) Chrome/24.0.1312.27 Safari/537.17"
request = urllib.request.Request(url, headers = headers)
resp = urllib.request.urlopen(request)
respData = str(resp.read())
return respData
except Exception as e:
print(str(e))
else: #If the Current Version of Python is 2.x
import urllib2
try:
headers = {}
headers['User-Agent'] = "Mozilla/5.0 (X11; Linux i686) AppleWebKit/537.17 (KHTML, like Gecko) Chrome/24.0.1312.27 Safari/537.17"
request = urllib2.Request(url, headers = headers)
try:
response = urllib2.urlopen(request)
except URLError: # Handling SSL certificate failed
context = ssl._create_unverified_context()
response = urlopen(req,context=context)
#response = urllib2.urlopen(req)
raw_html = response.read()
return raw_html
except:
return"Page Not found"
def next_link(s):
start_line = s.find('rg_di')
if start_line == -1: #If no links are found then give an error!
end_quote = 0
link = "no_links"
return link, end_quote
else:
start_line = s.find('"class="rg_meta"')
start_content = s.find('"ou"',start_line+1)
end_content = s.find(',"ow"',start_content+1)
content_raw = str(s[start_content+6:end_content-1])
return content_raw, end_content
def all_links(page):
links = []
while True:
link, end_content = next_link(page)
if link == "no_links":
break
else:
links.append(link) #Append all the links in the list named 'Links'
#time.sleep(0.1) #Timer could be used to slow down the request for image downloads
page = page[end_content:]
return links
def download_images(links, search_keyword):
choice = input("Do you want to save the links? [y]/[n]: ")
if choice=='y' or choice=='Y':
#write all the links into a test file.
f = open('links.txt', 'a') #Open the text file called links.txt
for link in links:
f.write(str(link))
f.write("\n")
f.close() #Close the file
num = input("Enter number of images to download (max 100): ")
counter = 1
errors=0
search_keyword = search_keyword.replace("%20","_")
directory = search_keyword+'/'
if not os.path.isdir(directory):
os.makedirs(directory)
pbar = ProgressBar()
for link in pbar(links):
if counter<=int(num):
file_extension = link.split(".")[-1]
filename = directory + str(counter) + "."+ file_extension
#print ("Downloading image: " + str(counter)+'/'+str(num))
try:
urllib.request.urlretrieve(link, filename)
except IOError:
errors+=1
#print ("\nIOError on Image" + str(counter))
except urllib.error.HTTPError as e:
errors+=1
#print ("\nHTTPError on Image"+ str(counter))
except urllib.error.URLError as e:
errors+=1
#print ("\nURLError on Image" + str(counter))
counter+=1
return errors
def search():
version = (3,0)
curr_version = sys.version_info
if curr_version >= version: #If the Current Version of Python is 3.0 or above
import urllib.request #urllib library for Extracting web pages
else:
import urllib2 #If current version of python is 2.x
search_keyword = input("Enter the search query: ")
#Download Image Links
links = []
search_keyword = search_keyword.replace(" ","%20")
url = 'https://www.google.com/search?q=' + search_keyword+ '&espv=2&biw=1366&bih=667&site=webhp&source=lnms&tbm=isch&sa=X&ei=XosDVaCXD8TasATItgE&ved=0CAcQ_AUoAg'
raw_html = (get_raw_html(url))
links = links + (all_links(raw_html))
print ("Total Image Links = "+str(len(links)))
print ("\n")
errors = download_images(links, search_keyword)
print ("Download Complete.\n"+ str(errors) +" errors while downloading.")
search()
In this python project I make a search in unsplash.com, which brings me a list of URL, then I save a number of them (pre-defined by the user) to a pre-defined folder. Check it out.
On Windows, install wget - https://sourceforge.net/projects/gnuwin32/files/wget/1.11.4-1/
and add C:\\Program Files (x86)\\GnuWin32\\bin to your environment path.
create a folder with a txt file of all the images you want to download.
in the location bar at the top of the file explorer type cmd
When the command prompt opens enter the following.
wget -i images.txt --no-check-certificate
Currently running Windows 7 and wanting to download a list of URLs without downloading any wget.exe or other dependency (which would be simplest as the first command) the shortest compatible way is a power-shell command (not my favorite for speed, but if needs must.)
The file with URLs is filelist.txt
and IWR
is the PS near equivalent of wget
.
The Security Protocol first command ensures we are using modern TLS1.2 protocol
-OutF ... split-path ...
means the filenames will be the same but at CWD (current working directory), for scripting you can cd /d folder
if necessary.
PS> [Net.ServicePointManager]::SecurityProtocol = "Tls12" ; GC filelist.txt | % {IWR $_ -OutF $(Split-Path $_ -Leaf)}
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.