I am having a problem naming the file I have downloaded and assigning it a file type. (see on line 4 of the code).
Saving the file in any location, I specifically assign to it. not in the same directory as the program. e.g in Downloads, documents, or any directory.
import requests
downloadUrl = input('Enter URL: ')
file_url = requests.get(downloadUrl)
dir_path = input("Enter path and name of the file: ")
f = open(dir_path,'a+')
Any inputs?
You are opening a requests object not a file path
file_url = requests.get(downloadUrl)
with open(file_url, 'w+') as f:
You would need to open a filepath on disk somewhere and write to that
See Using the request Module on https://stackabuse.com/download-files-with-python/
EDIT: From comments on post
In [584]: link = "https://www.annualreports.com/HostedData/AnnualReportArchive/3/NASDAQ_QFIN_2018.pdf"
In [585]: import requests
In [586]: file_url = requests.get(link)
In [587]: with open('/tmp/NASDAQ_QFIN_2018.pdf', 'wb') as f:
...: f.write(file_url.content)
...:
In [588]: ls -al /tmp/NASDAQ_QFIN_2018.pdf
-rw-r--r-- 1 ME wheel 1796199 9 Apr 15:21 /tmp/NASDAQ_QFIN_2018.pdf
Related
I'm writing a program to take large PDF's and convert each page to a .jpg, then add the .jpg's of each pdf file to their own directory (which the program needs to create).
I have completed the conversion part of the program, but I am stuck on creating a directory and adding the files to the directory.
Here's my code so far.
import glob, sys, fitz, os, shutil
zoom_x = 2.0
zoom_y = 2.0
mat = fitz.Matrix(zoom_x, zoom_y) # to get better resolution
all_files = glob.glob('/Users/homefolder/Downloads/*.pdf') # image path
print(all_files)
for filename in all_files:
doc = fitz.open(filename)
head, tail = os.path.split(doc.name)
save_file_name = tail.split('.')[0]
for page in doc: # iterate through the pages
# print(page)
pix = page.get_pixmap(matrix=mat)
# render the image
filepath_save = '/Users/homefolder/Downloads/files' + save_file_name + str(page.number) + '.jpg'
pix.save(filepath_save) # save image
sample = glob.glob('/Users/homefolder/Downloads/*.jpg')
How would I write the code to create a directory for each pdf file and add those .jpg's to the directory?
You can create directory and save to it your processed files, I also refactored your code a bit:
import glob, fitz, os
zoom_x = 2.0
zoom_y = 2.0
mat = fitz.Matrix(zoom_x, zoom_y)
pdf_files = glob.glob('/Users/homefolder/Downloads/*.pdf')
save_to = '/Users/homefolder/Downloads/pdf_as_img/'
for path in pdf_files:
doc = fitz.open(path)
base_name, _ = os.path.splitext(os.path.basename(doc.name))
directory_to_save = os.path.join(save_to, base_name)
if not os.path.exists(directory_to_save):
os.makedirs(directory_to_save)
for page in doc:
pix = page.get_pixmap(matrix=mat)
filepath_save = os.path.join(directory_to_save, str(page.number) + '.jpg')
pix.save(filepath_save)
This script creates a directory for every pdf file and saves pages as jpg to it.
I am trying to download documents (mainly in pdf) from a large number of web links like the following:
https://projects.worldbank.org/en/projects-operations/document-detail/P167897?type=projects
https://projects.worldbank.org/en/projects-operations/document-detail/P173997?type=projects
https://projects.worldbank.org/en/projects-operations/document-detail/P166309?type=projects
However, the pdf files are not directly accessible from these links. One needs to click on sub-URLs to access the pdfs. Is there any way to crawl the sub-URLs and download all the related files from them? I am trying it with the following codes but have not had any success so far specifically for these URLs listed here.
Please let me know if you need any further clarifications. I would be happy to do so. Thank you.
from simplified_scrapy import Spider, SimplifiedDoc, SimplifiedMain, utils
class MySpider(Spider):
name = 'download_pdf'
allowed_domains = ["www.worldbank.org"]
start_urls = [
"https://projects.worldbank.org/en/projects-operations/document-detail/P167897?type=projects",
"https://projects.worldbank.org/en/projects-operations/document-detail/P173997?type=projects",
"https://projects.worldbank.org/en/projects-operations/document-detail/P166309?type=projects"
] # Entry page
def afterResponse(self, response, url, error=None, extra=None):
if not extra:
print ("The version of library simplified_scrapy is too old, please update.")
SimplifiedMain.setRunFlag(False)
return
try:
path = './pdfs'
# create folder start
srcUrl = extra.get('srcUrl')
if srcUrl:
index = srcUrl.find('year/')
year = ''
if index > 0:
year = srcUrl[index + 5:]
index = year.find('?')
if index>0:
path = path + year[:index]
utils.createDir(path)
# create folder end
path = path + url[url.rindex('/'):]
index = path.find('?')
if index > 0: path = path[:index]
flag = utils.saveResponseAsFile(response, path, fileType="pdf")
if flag:
return None
else: # If it's not a pdf, leave it to the frame
return Spider.afterResponse(self, response, url, error, extra)
except Exception as err:
print(err)
def extract(self, url, html, models, modelNames):
doc = SimplifiedDoc(html)
lst = doc.selects('div.list >a').contains("documents/", attr="href")
if not lst:
lst = doc.selects('div.hidden-md hidden-lg >a')
urls = []
for a in lst:
a["url"] = utils.absoluteUrl(url.url, a["href"])
# Set root url start
a["srcUrl"] = url.get('srcUrl')
if not a['srcUrl']:
a["srcUrl"] = url.url
# Set root url end
urls.append(a)
return {"Urls": urls}
# Download again by resetting the URL. Called when you want to download again.
def resetUrl(self):
Spider.clearUrl(self)
Spider.resetUrlsTest(self)
SimplifiedMain.startThread(MySpider()) # Start download
There's an API endpoint that contains the entire response you see on the web-site along with... the URL to the document pdf. :D
So, you can query the API, get the URLS, and finally fetch the documents.
Here's how:
import requests
pids = ["P167897", "P173997", "P166309"]
for pid in pids:
end_point = f"https://search.worldbank.org/api/v2/wds?" \
f"format=json&includepublicdocs=1&" \
f"fl=docna,lang,docty,repnb,docdt,doc_authr,available_in&" \
f"os=0&rows=20&proid={pid}&apilang=en"
documents = requests.get(end_point).json()["documents"]
for document_data in documents.values():
try:
pdf_url = document_data["pdfurl"]
print(f"Fetching: {pdf_url}")
with open(pdf_url.rsplit("/")[-1], "wb") as pdf:
pdf.write(requests.get(pdf_url).content)
except KeyError:
continue
Output: (fully downloaded .pdf files)
Fetching: http://documents.worldbank.org/curated/en/106981614570591392/pdf/Official-Documents-Grant-Agreement-for-Additional-Financing-Grant-TF0B4694.pdf
Fetching: http://documents.worldbank.org/curated/en/331341614570579132/pdf/Official-Documents-First-Restatement-to-the-Disbursement-Letter-for-Grant-D6810-SL-and-for-Additional-Financing-Grant-TF0B4694.pdf
Fetching: http://documents.worldbank.org/curated/en/387211614570564353/pdf/Official-Documents-Amendment-to-the-Financing-Agreement-for-Grant-D6810-SL.pdf
Fetching: http://documents.worldbank.org/curated/en/799541612993594209/pdf/Sierra-Leone-AFRICA-WEST-P167897-Sierra-Leone-Free-Education-Project-Procurement-Plan.pdf
Fetching: http://documents.worldbank.org/curated/en/310641612199201329/pdf/Disclosable-Version-of-the-ISR-Sierra-Leone-Free-Education-Project-P167897-Sequence-No-02.pdf
and more ...
I am trying to donwload a huge zip file (~9Go zipped and ~130GO unzipped) from an FTP with python using the ftplib library but unfortunately when using the retrbinary method, it does create the file in my local diretory but it is not writing into the file. After a while the code runs, I get an timeout error. It used to work fine before, but when I tried to go deeper in the use of sockets by using this code it does not work anymore. Indeed, as the files I am trying to download are huge I want to have more control with the connection to prevent timeout error while downloading the files. I am not very familar with sockets so I may have misused it. I have been searching online but did not find any problems like this. (I tried with smaller files too for test but still have the same issues)
Here are the function that I tried but both have problems (method 1 is not writing to file, method 2 donwloads file but I can't unzip it)
import time
import socket
import ftplib
import threading
# To complete
filename = ''
local_folder = ''
ftp_folder = ''
host = ''
user = ''
mp = ''
# timeout error in method 1
def downloadFile_method_1(filename, local_folder, ftp_folder, host, user, mp):
try:
ftp = ftplib.FTP(host, user, mp, timeout=1600)
ftp.set_debuglevel(2)
except ftplib.error_perm as error:
print(error)
with open(local_folder + '/' + filename, "wb") as f:
ftp.retrbinary("RETR" + ftp_folder + '/' + filename, f.write)
# method 2 works to download zip file, but header error when unziping it
def downloadFile_method_2(filename, local_folder, ftp_folder, host, user, mp):
try:
ftp = ftplib.FTP(host, user, mp, timeout=1600)
ftp.set_debuglevel(2)
sock = ftp.transfercmd('RETR ' + ftp_folder + '/' + filename)
except ftplib.error_perm as error:
print(error)
def background():
f = open(local_folder + '/' + filename, 'wb')
while True:
block = sock.recv(1024*1024)
if not block:
break
f.write(block)
sock.close()
t = threading.Thread(target=background)
t.start()
while t.is_alive():
t.join(60)
ftp.voidcmd('NOOP')
def unzip_file(filename, local_folder):
local_filename = local_folder + '/' + filename
with ZipFile(local_filename, 'r') as zipObj:
zipObj.extractall(local_folder)
And the error I get for method 1:
ftplib.error_temp: 421 Timeout - try typing a little faster next time
And the error I get when I try to unzip after using method 2:
zipfile.BadZipFile: Bad magic number for file header
Alos, regarding this code If anyone could explain what this does concerning socketopt too would be helpful:
ftp.sock.setsockopt(socket.SOL_SOCKET, socket.SO_KEEPALIVE, 1)
ftp.sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_KEEPINTVL, 75)
ftp.sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_KEEPIDLE, 60)
Thanks for your help.
So far I have the following:
source_folder = 'file_location'
for file in os.listdir(source_folder):
if file.startswith('stnet_'):
os.rename(file, file.replace('stnet_a_b', '%s_' % time.ctime(os.path.getctime(file)) + 'stnet_a_b'))
The issue with is is I keep getting FileNotFoundError: [WinError 2] The system cannot find the file specified 'stnet_a_b.raw'
Can someone point out what I'm doing wrong?
Thanks.
os.listdir can only get the filenames without directory, while os.rename, os.path.getctime needs full name with directory(if your current directory is not conincidently file_location then the file will not be found).
You can use os.path.join to get the full name. And if you are on Windows you must make sure filename doesn't contain special characters which your code contains.
dir = r'file_location'
# os.chdir(dir) # in case you don't want to use os.path.join
for filename in os.listdir(dir):
print(filename)
if filename.startswith('stnet_'):
src = os.path.join(dir, filename)
ctime_str = str(time.ctime(os.path.getctime(src)))
ctime_str = ctime_str.replace(':', '').replace(' ', '') # remove special characters
fn_new = filename.replace('stnet_a_b',
'{}_'.format(ctime_str + 'stnet_a_b'))
des = os.path.join(dir, fn_new)
print('src={}, des={}'.format(src, des))
os.rename(src, des)
please try above code.
I have set up 3 Google Cloud Storge buckets and 3 functions (one for each bucket) that will trigger when a PDF file is uploaded to a bucket. Functions convert PDF to png image and do further processing.
When I am trying to create a 4th bucket and similar function, strangely it is not working. Even if I copy one of the existing 3 functions, it is still not working and I am getting this error:
Traceback (most recent call last): File "/env/local/lib/python3.7/site-packages/google/cloud/functions_v1beta2/worker.py", line 333, in run_background_function _function_handler.invoke_user_function(event_object) File "/env/local/lib/python3.7/site-packages/google/cloud/functions_v1beta2/worker.py", line 199, in invoke_user_function return call_user_function(request_or_event) File "/env/local/lib/python3.7/site-packages/google/cloud/functions_v1beta2/worker.py", line 196, in call_user_function event_context.Context(**request_or_event.context)) File "/user_code/main.py", line 27, in pdf_to_img with Image(filename=tmp_pdf, resolution=300) as image: File "/env/local/lib/python3.7/site-packages/wand/image.py", line 2874, in __init__ self.read(filename=filename, resolution=resolution) File "/env/local/lib/python3.7/site-packages/wand/image.py", line 2952, in read self.raise_exception() File "/env/local/lib/python3.7/site-packages/wand/resource.py", line 222, in raise_exception raise e wand.exceptions.PolicyError: not authorized/tmp/tmphm3hiezy' # error/constitute.c/ReadImage/412`
It is baffling me why same functions are working on existing buckets but not on new one.
UPDATE:
Even this is not working (getting "cache resources exhausted" error):
In requirements.txt:
google-cloud-storage
wand
In main.py:
import tempfile
from google.cloud import storage
from wand.image import Image
storage_client = storage.Client()
def pdf_to_img(data, context):
file_data = data
pdf = file_data['name']
if pdf.startswith('v-'):
return
bucket_name = file_data['bucket']
blob = storage_client.bucket(bucket_name).get_blob(pdf)
_, tmp_pdf = tempfile.mkstemp()
_, tmp_png = tempfile.mkstemp()
tmp_png = tmp_png+".png"
blob.download_to_filename(tmp_pdf)
with Image(filename=tmp_pdf) as image:
image.save(filename=tmp_png)
print("Image created")
new_file_name = "v-"+pdf.split('.')[0]+".png"
blob.bucket.blob(new_file_name).upload_from_filename(tmp_png)
Above code is supposed to just create a copy of image file which is uploaded to bucket.
Because the vulnerability has been fixed in Ghostscript but not updated in ImageMagick, the workaround for converting PDFs to images in Google Cloud Functions is to use this ghostscript wrapper and directly request the PDF conversion to png from Ghostscript (bypassing ImageMagick).
requirements.txt
google-cloud-storage
ghostscript==0.6
main.py
import locale
import tempfile
import ghostscript
from google.cloud import storage
storage_client = storage.Client()
def pdf_to_img(data, context):
file_data = data
pdf = file_data['name']
if pdf.startswith('v-'):
return
bucket_name = file_data['bucket']
blob = storage_client.bucket(bucket_name).get_blob(pdf)
_, tmp_pdf = tempfile.mkstemp()
_, tmp_png = tempfile.mkstemp()
tmp_png = tmp_png+".png"
blob.download_to_filename(tmp_pdf)
# create a temp folder based on temp_local_filename
# use ghostscript to export the pdf into pages as pngs in the temp dir
args = [
"pdf2png", # actual value doesn't matter
"-dSAFER",
"-sDEVICE=pngalpha",
"-o", tmp_png,
"-r300", tmp_pdf
]
# the above arguments have to be bytes, encode them
encoding = locale.getpreferredencoding()
args = [a.encode(encoding) for a in args]
#run the request through ghostscript
ghostscript.Ghostscript(*args)
print("Image created")
new_file_name = "v-"+pdf.split('.')[0]+".png"
blob.bucket.blob(new_file_name).upload_from_filename(tmp_png)
Anyway, this gets you around the issue and keeps all the processing in GCF for you. Hope it helps. Your code works for single page PDFs though. My use-case was for multipage pdf conversion, ghostscript code & solution in this question.
This actually seems to be a show stopper for ImageMagick related functionalities using PDF format. Similar code deployed by us on Google App engine via custom docker is failing with the same error on missing authorizations.
I am not sure how to edit the policy.xml file on GAE or GCF but a line there has to be changed to:
<policy domain="coder" rights="read|write" pattern="PDF" />
#Dustin: Do you have a bug link where we can see the progress ?
Update:
I fixed it on my Google app engine container by adding a line in docker image. This directly changes the policy.xml file content after imagemagick gets installed.
RUN sed -i 's/rights="none"/rights="read|write"/g' /etc/ImageMagick-6/policy.xml
This is an upstream bug in Ubuntu, we are working on a workaround for App Engine and Cloud Functions.
While we wait for the issue to be resolved in Ubuntu, I followed #DustinIngram's suggestion and created a virtual machine in Compute Engine with an ImageMagick installation. The downside is that I now have a second API that my API in App Engine has to call, just to generate the images. Having said that, it's working fine for me. This is my setup:
Main API:
When a pdf file is uploaded to Cloud Storage, I call the following:
response = requests.post('http://xx.xxx.xxx.xxx:5000/makeimages', data=data)
Where data is a JSON string with the format {"file_name": file_name}
On the API that is running on the VM, the POST request gets processed as follows:
#app.route('/makeimages', methods=['POST'])
def pdf_to_jpg():
file_name = request.form['file_name']
blob = storage_client.bucket(bucket_name).get_blob(file_name)
_, temp_local_filename = tempfile.mkstemp()
temp_local_filename_jpeg = temp_local_filename + '.jpg'
# Download file from bucket.
blob.download_to_filename(temp_local_filename)
print('Image ' + file_name + ' was downloaded to ' + temp_local_filename)
with Image(filename=temp_local_filename, resolution=300) as img:
pg_num = 0
image_files = {}
image_files['pages'] = []
for img_page in img.sequence:
img_page_2 = Image(image=img_page)
img_page_2.format = 'jpeg'
img_page_2.compression_quality = 70
img_page_2.save(filename=temp_local_filename_jpeg)
new_file_name = file_name.replace('.pdf', 'p') + str(pg_num) + '.jpg'
new_blob = blob.bucket.blob(new_file_name)
new_blob.upload_from_filename(temp_local_filename_jpeg)
print('Page ' + str(pg_num) + ' was saved as ' + new_file_name)
image_files['pages'].append({'page': pg_num, 'file_name': new_file_name})
pg_num += 1
try:
os.remove(temp_local_filename)
except (ValueError, PermissionError):
print('Could not delete the temp file!')
return jsonify(image_files)
This will download the pdf from Cloud Storage, create an image for each page, and save them back to cloud storage. The API will then return a JSON file with the list of image files created.
So, not the most elegant solution, but at least I don't need to convert the files manually.