Image crawling using flask and beautiful soup process does not exits
.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty height:90px;width:728px;box-sizing:border-box;
1
I am creating an app to crawl images from a website using flask to get user input. But, the application process does not end and keeps on giving this message in the terminal. I actually want to terminate flask after the images are crawled
"127.0.0.1 - - [14/Nov/2018 12:00:44] "GET /static/script.js HTTP/1.1"
304 -"
import os
import sys
import urllib.request
import requests
from urllib.parse import urljoin
from bs4 import BeautifulSoup
from flask import Flask, render_template, request, redirect
ic = Flask(__name__)
count = 0
@ic.route("/")
def main():
if count == 1:
return render_template("index.html", result=str((str(count) + " Image Downloaded !")))
else:
return render_template("index.html", result=str((str(count) + " Images Downloaded !")))
@ic.route("/get_images", methods=['POST'])
def get_images():
_url = request.form['inputURL']
try:
global count
count = 0
code = requests.get(_url)
text = code.text
soup = BeautifulSoup(text)
for img in soup.findAll('img'):
count += 1
if (img.get('src'))[0:4] == 'http':
src = img.get('src')
else:
src = urljoin(_url, img.get('src'))
download_image(src, count)
return redirect("http://localhost:5000")
except requests.exceptions.HTTPError as error:
return render_template("index.html", result=str(error))
def download_image(url, num):
try:
image_name = str(num) + ".png"
image_path = os.path.join("images/", image_name)
urllib.request.urlretrieve(url, image_path)
except ValueError:
print("Invalid URL !")
except:
print("Unknown Exception" + str(sys.exc_info()[0]))
if __name__ == "__main__":
ic.run()
index.html
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta http-equiv="refresh" content="100;url=http://localhost:5000/"/>
<title>Image Crawler</title>
<link href="../static/style.css" rel="stylesheet">
</head>
<body class="body">
<div class="container">
<div class="header">
<h3 class="text-muted">Image Crawler</h3>
</div>
<div class="jumbotron">
<form name="myForm" class="form" onsubmit="return checkURL()" method="post" action="/get_images">
<h1>Enter URL</h1>
<input type="name" name="inputURL" class="input-text" id="inputURL" placeholder="URL"
required autofocus>
<br>
<button class="btn" id="btnSubmit" type="submit">Download Photos!</button>
</form>
</div>
<div class="jumbotron">
<h3> result </h3>
</div>
</div>
</body>
</html>
python flask beautifulsoup web-crawler
asked Nov 14 '18 at 7:00
Samrat ShresthaSamrat Shrestha
326
add a comment |
1
I am creating an app to crawl images from a website using flask to get user input. But, the application process does not end and keeps on giving this message in the terminal. I actually want to terminate flask after the images are crawled
"127.0.0.1 - - [14/Nov/2018 12:00:44] "GET /static/script.js HTTP/1.1"
304 -"
import os
import sys
import urllib.request
import requests
from urllib.parse import urljoin
from bs4 import BeautifulSoup
from flask import Flask, render_template, request, redirect
ic = Flask(__name__)
count = 0
@ic.route("/")
def main():
if count == 1:
return render_template("index.html", result=str((str(count) + " Image Downloaded !")))
else:
return render_template("index.html", result=str((str(count) + " Images Downloaded !")))
@ic.route("/get_images", methods=['POST'])
def get_images():
_url = request.form['inputURL']
try:
global count
count = 0
code = requests.get(_url)
text = code.text
soup = BeautifulSoup(text)
for img in soup.findAll('img'):
count += 1
if (img.get('src'))[0:4] == 'http':
src = img.get('src')
else:
src = urljoin(_url, img.get('src'))
download_image(src, count)
return redirect("http://localhost:5000")
except requests.exceptions.HTTPError as error:
return render_template("index.html", result=str(error))
def download_image(url, num):
try:
image_name = str(num) + ".png"
image_path = os.path.join("images/", image_name)
urllib.request.urlretrieve(url, image_path)
except ValueError:
print("Invalid URL !")
except:
print("Unknown Exception" + str(sys.exc_info()[0]))
if __name__ == "__main__":
ic.run()
index.html
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta http-equiv="refresh" content="100;url=http://localhost:5000/"/>
<title>Image Crawler</title>
<link href="../static/style.css" rel="stylesheet">
</head>
<body class="body">
<div class="container">
<div class="header">
<h3 class="text-muted">Image Crawler</h3>
</div>
<div class="jumbotron">
<form name="myForm" class="form" onsubmit="return checkURL()" method="post" action="/get_images">
<h1>Enter URL</h1>
<input type="name" name="inputURL" class="input-text" id="inputURL" placeholder="URL"
required autofocus>
<br>
<button class="btn" id="btnSubmit" type="submit">Download Photos!</button>
</form>
</div>
<div class="jumbotron">
<h3> result </h3>
</div>
</div>
</body>
</html>
python flask beautifulsoup web-crawler
asked Nov 14 '18 at 7:00
Samrat ShresthaSamrat Shrestha
326
Does it download images when you give it url ? And do you have input in terminal something likeGET / HTTP 1.1 200after you submit your form ?
– Dinko Pehar
Nov 14 '18 at 8:51
Yes it downloads the image. But after all the images are downloaded the process is not terminated
– Samrat Shrestha
Nov 14 '18 at 8:58
Can you provide me index.html ?
– Dinko Pehar
Nov 14 '18 at 9:26
I think I am having problem because I am not able to terminate the flask
– Samrat Shrestha
Nov 14 '18 at 9:31
add a comment |
1
1
1
I am creating an app to crawl images from a website using flask to get user input. But, the application process does not end and keeps on giving this message in the terminal. I actually want to terminate flask after the images are crawled
"127.0.0.1 - - [14/Nov/2018 12:00:44] "GET /static/script.js HTTP/1.1"
304 -"
import os
import sys
import urllib.request
import requests
from urllib.parse import urljoin
from bs4 import BeautifulSoup
from flask import Flask, render_template, request, redirect
ic = Flask(__name__)
count = 0
@ic.route("/")
def main():
if count == 1:
return render_template("index.html", result=str((str(count) + " Image Downloaded !")))
else:
return render_template("index.html", result=str((str(count) + " Images Downloaded !")))
@ic.route("/get_images", methods=['POST'])
def get_images():
_url = request.form['inputURL']
try:
global count
count = 0
code = requests.get(_url)
text = code.text
soup = BeautifulSoup(text)
for img in soup.findAll('img'):
count += 1
if (img.get('src'))[0:4] == 'http':
src = img.get('src')
else:
src = urljoin(_url, img.get('src'))
download_image(src, count)
return redirect("http://localhost:5000")
except requests.exceptions.HTTPError as error:
return render_template("index.html", result=str(error))
def download_image(url, num):
try:
image_name = str(num) + ".png"
image_path = os.path.join("images/", image_name)
urllib.request.urlretrieve(url, image_path)
except ValueError:
print("Invalid URL !")
except:
print("Unknown Exception" + str(sys.exc_info()[0]))
if __name__ == "__main__":
ic.run()
index.html
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta http-equiv="refresh" content="100;url=http://localhost:5000/"/>
<title>Image Crawler</title>
<link href="../static/style.css" rel="stylesheet">
</head>
<body class="body">
<div class="container">
<div class="header">
<h3 class="text-muted">Image Crawler</h3>
</div>
<div class="jumbotron">
<form name="myForm" class="form" onsubmit="return checkURL()" method="post" action="/get_images">
<h1>Enter URL</h1>
<input type="name" name="inputURL" class="input-text" id="inputURL" placeholder="URL"
required autofocus>
<br>
<button class="btn" id="btnSubmit" type="submit">Download Photos!</button>
</form>
</div>
<div class="jumbotron">
<h3> result </h3>
</div>
</div>
</body>
</html>
python flask beautifulsoup web-crawler
asked Nov 14 '18 at 7:00
Samrat ShresthaSamrat Shrestha
326
I am creating an app to crawl images from a website using flask to get user input. But, the application process does not end and keeps on giving this message in the terminal. I actually want to terminate flask after the images are crawled
"127.0.0.1 - - [14/Nov/2018 12:00:44] "GET /static/script.js HTTP/1.1"
304 -"
import os
import sys
import urllib.request
import requests
from urllib.parse import urljoin
from bs4 import BeautifulSoup
from flask import Flask, render_template, request, redirect
ic = Flask(__name__)
count = 0
@ic.route("/")
def main():
if count == 1:
return render_template("index.html", result=str((str(count) + " Image Downloaded !")))
else:
return render_template("index.html", result=str((str(count) + " Images Downloaded !")))
@ic.route("/get_images", methods=['POST'])
def get_images():
_url = request.form['inputURL']
try:
global count
count = 0
code = requests.get(_url)
text = code.text
soup = BeautifulSoup(text)
for img in soup.findAll('img'):
count += 1
if (img.get('src'))[0:4] == 'http':
src = img.get('src')
else:
src = urljoin(_url, img.get('src'))
download_image(src, count)
return redirect("http://localhost:5000")
except requests.exceptions.HTTPError as error:
return render_template("index.html", result=str(error))
def download_image(url, num):
try:
image_name = str(num) + ".png"
image_path = os.path.join("images/", image_name)
urllib.request.urlretrieve(url, image_path)
except ValueError:
print("Invalid URL !")
except:
print("Unknown Exception" + str(sys.exc_info()[0]))
if __name__ == "__main__":
ic.run()
index.html
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta http-equiv="refresh" content="100;url=http://localhost:5000/"/>
<title>Image Crawler</title>
<link href="../static/style.css" rel="stylesheet">
</head>
<body class="body">
<div class="container">
<div class="header">
<h3 class="text-muted">Image Crawler</h3>
</div>
<div class="jumbotron">
<form name="myForm" class="form" onsubmit="return checkURL()" method="post" action="/get_images">
<h1>Enter URL</h1>
<input type="name" name="inputURL" class="input-text" id="inputURL" placeholder="URL"
required autofocus>
<br>
<button class="btn" id="btnSubmit" type="submit">Download Photos!</button>
</form>
</div>
<div class="jumbotron">
<h3> result </h3>
</div>
</div>
</body>
</html>
python flask beautifulsoup web-crawler
python flask beautifulsoup web-crawler
asked Nov 14 '18 at 7:00
Samrat ShresthaSamrat Shrestha
326
asked Nov 14 '18 at 7:00
Samrat ShresthaSamrat Shrestha
326
edited Nov 14 '18 at 9:58
Samrat Shrestha
asked Nov 14 '18 at 7:00
Samrat ShresthaSamrat Shrestha
326
asked Nov 14 '18 at 7:00
Samrat ShresthaSamrat Shrestha
326
asked Nov 14 '18 at 7:00
Samrat ShresthaSamrat Shrestha
326
326
Does it download images when you give it url ? And do you have input in terminal something likeGET / HTTP 1.1 200after you submit your form ?
– Dinko Pehar
Nov 14 '18 at 8:51
Yes it downloads the image. But after all the images are downloaded the process is not terminated
– Samrat Shrestha
Nov 14 '18 at 8:58
Can you provide me index.html ?
– Dinko Pehar
Nov 14 '18 at 9:26
I think I am having problem because I am not able to terminate the flask
– Samrat Shrestha
Nov 14 '18 at 9:31
add a comment |
Does it download images when you give it url ? And do you have input in terminal something likeGET / HTTP 1.1 200after you submit your form ?
– Dinko Pehar
Nov 14 '18 at 8:51
Yes it downloads the image. But after all the images are downloaded the process is not terminated
– Samrat Shrestha
Nov 14 '18 at 8:58
Can you provide me index.html ?
– Dinko Pehar
Nov 14 '18 at 9:26
I think I am having problem because I am not able to terminate the flask
– Samrat Shrestha
Nov 14 '18 at 9:31
Does it download images when you give it url ? And do you have input in terminal something like
GET / HTTP 1.1 200 after you submit your form ?– Dinko Pehar
Nov 14 '18 at 8:51
Does it download images when you give it url ? And do you have input in terminal something like
GET / HTTP 1.1 200 after you submit your form ?– Dinko Pehar
Nov 14 '18 at 8:51
Yes it downloads the image. But after all the images are downloaded the process is not terminated
– Samrat Shrestha
Nov 14 '18 at 8:58
Yes it downloads the image. But after all the images are downloaded the process is not terminated
– Samrat Shrestha
Nov 14 '18 at 8:58
Can you provide me index.html ?
– Dinko Pehar
Nov 14 '18 at 9:26
Can you provide me index.html ?
– Dinko Pehar
Nov 14 '18 at 9:26
I think I am having problem because I am not able to terminate the flask
– Samrat Shrestha
Nov 14 '18 at 9:31
I think I am having problem because I am not able to terminate the flask
– Samrat Shrestha
Nov 14 '18 at 9:31
add a comment |
1 Answer
1
active
oldest
votes
0
I tested out and reworked your problem and below is the solution that worked. There were many bugs and errors, but I fixed them. I won't test for your form, but if you provide and process good url, it will work probably. Comment if something goes wrong
import os
import sys
import urllib.request
import requests
from urllib.parse import urljoin
from bs4 import BeautifulSoup
from flask import Flask, render_template, request, redirect
ic = Flask(__name__)
count = 0
@ic.route("/", methods=['GET'])
def main():
if count == 1:
return render_template("index.html", result=str((str(count) + " Image Downloaded !")))
else:
return render_template("index.html", result=str((str(count) + " Images Downloaded !")))
@ic.route("/get_images", methods=['POST', 'GET'])
def get_images():
_url = 'https://www.bljesak.info' # PROVIDE URL HERE MANUALLY OR FROM A FORM
try:
global count
count = 0
code = requests.get(_url)
text = code.text
soup = BeautifulSoup(text, 'html.parser')
for img in soup.findAll('img'):
count += 1
print(img.get('src'))
if (img.get('src'))[0:4] == 'https':
src = img.get('src')
download_image(src, count)
else:
src = urljoin(_url, img.get('src'))
download_image(src, count)
return redirect("http://localhost:5000")
except requests.exceptions.HTTPError as error:
return render_template("index.html", result=str(error))
def download_image(url, num):
try:
image_name = str(num) + '.png'
image_path = os.path.join("images/", image_name)
print(image_name, image_path) # WAIT FOR ALL TO FINISH, IF THERE IS A LOT OF IMAGES, YOU NEED TO WAIT
urllib.request.urlretrieve(url, image_path)
except ValueError:
print("Invalid URL !")
except:
print("Unknown Exception" + str(sys.exc_info()[0]))
if __name__ == "__main__":
ic.run()
Also, you have input of type url if you want url. You don't need to use name type.
answered Nov 14 '18 at 9:46
Dinko PeharDinko Pehar
1,5533425
This didn't work. I got an error "The method is not allowed for the requested URL." I also tried with the url you had provided.
– Samrat Shrestha
Nov 14 '18 at 9:54
Did you copy mine code or just entered url ?
– Dinko Pehar
Nov 14 '18 at 10:02
I tried both but both didnt work
– Samrat Shrestha
Nov 14 '18 at 10:03
I added methods to flask decorators. Can you try that ? Btw, you must have images folder created before you start downloading. It should be at top of the project
– Dinko Pehar
Nov 14 '18 at 10:04
1
Yes, I have image folders but the process does not exits even with your code. I guess you are getting my problem
– Samrat Shrestha
Nov 14 '18 at 10:10
add a comment |
Your Answer
StackExchange.ifUsing("editor", function ()
StackExchange.using("externalEditor", function ()
StackExchange.using("snippets", function ()
StackExchange.snippets.init();
);
);
, "code-snippets");
StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "1"
;
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function()
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled)
StackExchange.using("snippets", function()
createEditor();
);
else
createEditor();
);
function createEditor()
StackExchange.prepareEditor(
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader:
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
,
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);
);
draft saved
draft discarded
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53294693%2fimage-crawling-using-flask-and-beautiful-soup-process-does-not-exits%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
0
I tested out and reworked your problem and below is the solution that worked. There were many bugs and errors, but I fixed them. I won't test for your form, but if you provide and process good url, it will work probably. Comment if something goes wrong
import os
import sys
import urllib.request
import requests
from urllib.parse import urljoin
from bs4 import BeautifulSoup
from flask import Flask, render_template, request, redirect
ic = Flask(__name__)
count = 0
@ic.route("/", methods=['GET'])
def main():
if count == 1:
return render_template("index.html", result=str((str(count) + " Image Downloaded !")))
else:
return render_template("index.html", result=str((str(count) + " Images Downloaded !")))
@ic.route("/get_images", methods=['POST', 'GET'])
def get_images():
_url = 'https://www.bljesak.info' # PROVIDE URL HERE MANUALLY OR FROM A FORM
try:
global count
count = 0
code = requests.get(_url)
text = code.text
soup = BeautifulSoup(text, 'html.parser')
for img in soup.findAll('img'):
count += 1
print(img.get('src'))
if (img.get('src'))[0:4] == 'https':
src = img.get('src')
download_image(src, count)
else:
src = urljoin(_url, img.get('src'))
download_image(src, count)
return redirect("http://localhost:5000")
except requests.exceptions.HTTPError as error:
return render_template("index.html", result=str(error))
def download_image(url, num):
try:
image_name = str(num) + '.png'
image_path = os.path.join("images/", image_name)
print(image_name, image_path) # WAIT FOR ALL TO FINISH, IF THERE IS A LOT OF IMAGES, YOU NEED TO WAIT
urllib.request.urlretrieve(url, image_path)
except ValueError:
print("Invalid URL !")
except:
print("Unknown Exception" + str(sys.exc_info()[0]))
if __name__ == "__main__":
ic.run()
Also, you have input of type url if you want url. You don't need to use name type.
answered Nov 14 '18 at 9:46
Dinko PeharDinko Pehar
1,5533425
This didn't work. I got an error "The method is not allowed for the requested URL." I also tried with the url you had provided.
– Samrat Shrestha
Nov 14 '18 at 9:54
Did you copy mine code or just entered url ?
– Dinko Pehar
Nov 14 '18 at 10:02
I tried both but both didnt work
– Samrat Shrestha
Nov 14 '18 at 10:03
I added methods to flask decorators. Can you try that ? Btw, you must have images folder created before you start downloading. It should be at top of the project
– Dinko Pehar
Nov 14 '18 at 10:04
1
Yes, I have image folders but the process does not exits even with your code. I guess you are getting my problem
– Samrat Shrestha
Nov 14 '18 at 10:10
add a comment |
0
I tested out and reworked your problem and below is the solution that worked. There were many bugs and errors, but I fixed them. I won't test for your form, but if you provide and process good url, it will work probably. Comment if something goes wrong
import os
import sys
import urllib.request
import requests
from urllib.parse import urljoin
from bs4 import BeautifulSoup
from flask import Flask, render_template, request, redirect
ic = Flask(__name__)
count = 0
@ic.route("/", methods=['GET'])
def main():
if count == 1:
return render_template("index.html", result=str((str(count) + " Image Downloaded !")))
else:
return render_template("index.html", result=str((str(count) + " Images Downloaded !")))
@ic.route("/get_images", methods=['POST', 'GET'])
def get_images():
_url = 'https://www.bljesak.info' # PROVIDE URL HERE MANUALLY OR FROM A FORM
try:
global count
count = 0
code = requests.get(_url)
text = code.text
soup = BeautifulSoup(text, 'html.parser')
for img in soup.findAll('img'):
count += 1
print(img.get('src'))
if (img.get('src'))[0:4] == 'https':
src = img.get('src')
download_image(src, count)
else:
src = urljoin(_url, img.get('src'))
download_image(src, count)
return redirect("http://localhost:5000")
except requests.exceptions.HTTPError as error:
return render_template("index.html", result=str(error))
def download_image(url, num):
try:
image_name = str(num) + '.png'
image_path = os.path.join("images/", image_name)
print(image_name, image_path) # WAIT FOR ALL TO FINISH, IF THERE IS A LOT OF IMAGES, YOU NEED TO WAIT
urllib.request.urlretrieve(url, image_path)
except ValueError:
print("Invalid URL !")
except:
print("Unknown Exception" + str(sys.exc_info()[0]))
if __name__ == "__main__":
ic.run()
Also, you have input of type url if you want url. You don't need to use name type.
answered Nov 14 '18 at 9:46
Dinko PeharDinko Pehar
1,5533425
This didn't work. I got an error "The method is not allowed for the requested URL." I also tried with the url you had provided.
– Samrat Shrestha
Nov 14 '18 at 9:54
Did you copy mine code or just entered url ?
– Dinko Pehar
Nov 14 '18 at 10:02
I tried both but both didnt work
– Samrat Shrestha
Nov 14 '18 at 10:03
I added methods to flask decorators. Can you try that ? Btw, you must have images folder created before you start downloading. It should be at top of the project
– Dinko Pehar
Nov 14 '18 at 10:04
1
Yes, I have image folders but the process does not exits even with your code. I guess you are getting my problem
– Samrat Shrestha
Nov 14 '18 at 10:10
add a comment |
0
0
0
I tested out and reworked your problem and below is the solution that worked. There were many bugs and errors, but I fixed them. I won't test for your form, but if you provide and process good url, it will work probably. Comment if something goes wrong
import os
import sys
import urllib.request
import requests
from urllib.parse import urljoin
from bs4 import BeautifulSoup
from flask import Flask, render_template, request, redirect
ic = Flask(__name__)
count = 0
@ic.route("/", methods=['GET'])
def main():
if count == 1:
return render_template("index.html", result=str((str(count) + " Image Downloaded !")))
else:
return render_template("index.html", result=str((str(count) + " Images Downloaded !")))
@ic.route("/get_images", methods=['POST', 'GET'])
def get_images():
_url = 'https://www.bljesak.info' # PROVIDE URL HERE MANUALLY OR FROM A FORM
try:
global count
count = 0
code = requests.get(_url)
text = code.text
soup = BeautifulSoup(text, 'html.parser')
for img in soup.findAll('img'):
count += 1
print(img.get('src'))
if (img.get('src'))[0:4] == 'https':
src = img.get('src')
download_image(src, count)
else:
src = urljoin(_url, img.get('src'))
download_image(src, count)
return redirect("http://localhost:5000")
except requests.exceptions.HTTPError as error:
return render_template("index.html", result=str(error))
def download_image(url, num):
try:
image_name = str(num) + '.png'
image_path = os.path.join("images/", image_name)
print(image_name, image_path) # WAIT FOR ALL TO FINISH, IF THERE IS A LOT OF IMAGES, YOU NEED TO WAIT
urllib.request.urlretrieve(url, image_path)
except ValueError:
print("Invalid URL !")
except:
print("Unknown Exception" + str(sys.exc_info()[0]))
if __name__ == "__main__":
ic.run()
Also, you have input of type url if you want url. You don't need to use name type.
answered Nov 14 '18 at 9:46
Dinko PeharDinko Pehar
1,5533425
I tested out and reworked your problem and below is the solution that worked. There were many bugs and errors, but I fixed them. I won't test for your form, but if you provide and process good url, it will work probably. Comment if something goes wrong
import os
import sys
import urllib.request
import requests
from urllib.parse import urljoin
from bs4 import BeautifulSoup
from flask import Flask, render_template, request, redirect
ic = Flask(__name__)
count = 0
@ic.route("/", methods=['GET'])
def main():
if count == 1:
return render_template("index.html", result=str((str(count) + " Image Downloaded !")))
else:
return render_template("index.html", result=str((str(count) + " Images Downloaded !")))
@ic.route("/get_images", methods=['POST', 'GET'])
def get_images():
_url = 'https://www.bljesak.info' # PROVIDE URL HERE MANUALLY OR FROM A FORM
try:
global count
count = 0
code = requests.get(_url)
text = code.text
soup = BeautifulSoup(text, 'html.parser')
for img in soup.findAll('img'):
count += 1
print(img.get('src'))
if (img.get('src'))[0:4] == 'https':
src = img.get('src')
download_image(src, count)
else:
src = urljoin(_url, img.get('src'))
download_image(src, count)
return redirect("http://localhost:5000")
except requests.exceptions.HTTPError as error:
return render_template("index.html", result=str(error))
def download_image(url, num):
try:
image_name = str(num) + '.png'
image_path = os.path.join("images/", image_name)
print(image_name, image_path) # WAIT FOR ALL TO FINISH, IF THERE IS A LOT OF IMAGES, YOU NEED TO WAIT
urllib.request.urlretrieve(url, image_path)
except ValueError:
print("Invalid URL !")
except:
print("Unknown Exception" + str(sys.exc_info()[0]))
if __name__ == "__main__":
ic.run()
Also, you have input of type url if you want url. You don't need to use name type.
answered Nov 14 '18 at 9:46
Dinko PeharDinko Pehar
1,5533425
edited Nov 14 '18 at 10:04
answered Nov 14 '18 at 9:46
Dinko PeharDinko Pehar
1,5533425
answered Nov 14 '18 at 9:46
Dinko PeharDinko Pehar
1,5533425
answered Nov 14 '18 at 9:46
Dinko PeharDinko Pehar
1,5533425
1,5533425
This didn't work. I got an error "The method is not allowed for the requested URL." I also tried with the url you had provided.
– Samrat Shrestha
Nov 14 '18 at 9:54
Did you copy mine code or just entered url ?
– Dinko Pehar
Nov 14 '18 at 10:02
I tried both but both didnt work
– Samrat Shrestha
Nov 14 '18 at 10:03
I added methods to flask decorators. Can you try that ? Btw, you must have images folder created before you start downloading. It should be at top of the project
– Dinko Pehar
Nov 14 '18 at 10:04
1
Yes, I have image folders but the process does not exits even with your code. I guess you are getting my problem
– Samrat Shrestha
Nov 14 '18 at 10:10
add a comment |
This didn't work. I got an error "The method is not allowed for the requested URL." I also tried with the url you had provided.
– Samrat Shrestha
Nov 14 '18 at 9:54
Did you copy mine code or just entered url ?
– Dinko Pehar
Nov 14 '18 at 10:02
I tried both but both didnt work
– Samrat Shrestha
Nov 14 '18 at 10:03
I added methods to flask decorators. Can you try that ? Btw, you must have images folder created before you start downloading. It should be at top of the project
– Dinko Pehar
Nov 14 '18 at 10:04
1
Yes, I have image folders but the process does not exits even with your code. I guess you are getting my problem
– Samrat Shrestha
Nov 14 '18 at 10:10
This didn't work. I got an error "The method is not allowed for the requested URL." I also tried with the url you had provided.
– Samrat Shrestha
Nov 14 '18 at 9:54
This didn't work. I got an error "The method is not allowed for the requested URL." I also tried with the url you had provided.
– Samrat Shrestha
Nov 14 '18 at 9:54
Did you copy mine code or just entered url ?
– Dinko Pehar
Nov 14 '18 at 10:02
Did you copy mine code or just entered url ?
– Dinko Pehar
Nov 14 '18 at 10:02
I tried both but both didnt work
– Samrat Shrestha
Nov 14 '18 at 10:03
I tried both but both didnt work
– Samrat Shrestha
Nov 14 '18 at 10:03
I added methods to flask decorators. Can you try that ? Btw, you must have images folder created before you start downloading. It should be at top of the project
– Dinko Pehar
Nov 14 '18 at 10:04
I added methods to flask decorators. Can you try that ? Btw, you must have images folder created before you start downloading. It should be at top of the project
– Dinko Pehar
Nov 14 '18 at 10:04
1
1
Yes, I have image folders but the process does not exits even with your code. I guess you are getting my problem
– Samrat Shrestha
Nov 14 '18 at 10:10
Yes, I have image folders but the process does not exits even with your code. I guess you are getting my problem
– Samrat Shrestha
Nov 14 '18 at 10:10
add a comment |
draft saved
draft discarded
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
draft saved
draft discarded
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53294693%2fimage-crawling-using-flask-and-beautiful-soup-process-does-not-exits%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Does it download images when you give it url ? And do you have input in terminal something like
GET / HTTP 1.1 200after you submit your form ?– Dinko Pehar
Nov 14 '18 at 8:51
Yes it downloads the image. But after all the images are downloaded the process is not terminated
– Samrat Shrestha
Nov 14 '18 at 8:58
Can you provide me index.html ?
– Dinko Pehar
Nov 14 '18 at 9:26
I think I am having problem because I am not able to terminate the flask
– Samrat Shrestha
Nov 14 '18 at 9:31