The goal is to download GTFS data through python web scraping, starting with https://transitfeeds.com/p/agence-metropolitaine-de-transport/129/latest/download
Currently, I'm using requests like so:
def download(url):
fpath = "prov/city/GTFS"
r = requests.get(url)
if r.ok:
print("Saving file.")
open(fpath, "wb").write(r.content)
else:
print("Download failed.")
The results of requests.content of the above url unfortunately renders the following:
You can see the files of interest within the output (e.g. stops.txt) but how might I access them to read/write?
I fear you're trying to read a zip file with a text editor, perhaps you should try using the "zipfile" module.
The following worked:
def download(url):
fpath = "path/to/output/"
f = requests.get(url, stream = True, headers = headers)
if f.ok:
print("Saving to {}".format(fpath))
g=open(fpath+'output.zip','wb')
g.write(f.content)
g.close()
else:
print("Download failed with error code: ", f.status_code)
You need to write this file into a zip.
import requests
url = "https://transitfeeds.com/p/agence-metropolitaine-de-transport/129/latest/download"
fname = "gtfs.zip"
r = requests.get(url)
open(fname, "wb").write(r.content)
Now fname exists and has several text files inside. If you want to programmatically extract this zip and then read the content of a file, for example stops.txt, then you need first to extract a single file, or simply extractall.
import zipfile
# this will extract only a single file, and
# raise a KeyError if the file is missing from the archive
zipfile.ZipFile(fname).extract("stops.txt")
# this will extract all the files found from the archive,
# overwriting files in the process
zipfile.ZipFile(fname).extractall()
Now you just need to work with your file(s).
thefile = "stops.txt"
# just plain text
text = open(thefile).read()
# csv file
import csv
reader = csv.reader(open(thefile))
for row in reader:
...
I am using the requests library to download a file from a URL. This is my code
for tag in soup.find_all('a'):
if '.zip' in str(tag):
file_name = str(tag).strip().split('>')[-2].split('<')[0]
link = link_name+tag.get('href')
r = requests.get(link, stream=True)
with open(os.path.join(download_path, file_name), 'wb') as fd:
for chunk in r.iter_content(chunk_size=1024):
if chunk:
fd.write(chunk)
And then I unzip the file using this code
unzip_path = os.path.join(download_path, file_name.split('.')[0])
with zipfile.ZipFile(os.path.join(download_path, file_name), 'r') as zip_ref:
zip_ref.extractall(unzip_path)
This code looks if there is a zip file in the provided page and then downloads the zipped file in a directory. Then it will unzip the file using the zipFile library.
The problem with this code is that sometimes the download is not complete. So for example if the zipped file is 312KB long only parts of it is downloaded. And then I get a BadZipFile error. But sometimes the entire file is downloaded correctly.
I tried the same without streaming and even that results in the same problem.
How do I check if all the chunks are downloaded properly.
Maybe this works:
r = requests.get(link)
with open(os.path.join(download_path, file_name), 'wb') as fd:
fd.write(r.content)
I am trying to download an image from an instagram media URL:
https://instagram.fybz2-1.fna.fbcdn.net/v/t51.2885-15/fr/e15/p1080x1080/106602453_613520712600632_6255422472318530180_n.jpg?_nc_ht=instagram.fybz2-1.fna.fbcdn.net&_nc_cat=108&_nc_ohc=WQizf6rhDmQAX883HrQ&oh=140f221889178fd03bf654cf18a9d9a2&oe=5F4D2AFE
Pasting this into my browser will bring up the image, but when I run the following code I get the following error which i suspect is due to issues with the URL containing a query string (running this on a simple url ending in .jpg works without issue
File "C:/Users/19053/InstagramImageDownloader/downloadImage.py", line 18, in <module>
with open(filename, 'wb') as f:
OSError: [Errno 22] Invalid argument: '106602453_613520712600632_6255422472318530180_n.jpg?_nc_ht=instagram.fybz2-1.fna.fbcdn.net&_nc_cat=108&_nc_ohc=WQizf6rhDmQAX883HrQ&oh=140f221889178fd03bf654cf18a9d9a2&oe=5F4D2AFE'
Full code as follows:
## Importing Necessary Modules
import requests # to get image from the web
import shutil # to save it locally
## Set up the image URL and filename
image_url = "https://instagram.fybz2-1.fna.fbcdn.net/v/t51.2885-15/fr/e15/p1080x1080/106602453_613520712600632_6255422472318530180_n.jpg?_nc_ht=instagram.fybz2-1.fna.fbcdn.net&_nc_cat=108&_nc_ohc=WQizf6rhDmQAX883HrQ&oh=140f221889178fd03bf654cf18a9d9a2&oe=5F4D2AFE"
filename = image_url.split("/")[-1]
# Open the url image, set stream to True, this will return the stream content.
r = requests.get(image_url, stream=True)
# Check if the image was retrieved successfully
if r.status_code == 200:
# Set decode_content value to True, otherwise the downloaded image file's size will be zero.
r.raw.decode_content = True
# Open a local file with wb ( write binary ) permission.
with open(filename, 'wb') as f:
shutil.copyfileobj(r.raw, f)
print('Image sucessfully Downloaded: ', filename)
else:
print('Image Couldn\'t be retreived')
The problem is with the filename. You need to first split by ? then take the first element then split by /
import requests # to get image from the web
import shutil # to save it locally
## Set up the image URL and filename
image_url = "https://instagram.fybz2-1.fna.fbcdn.net/v/t51.2885-15/fr/e15/p1080x1080/106602453_613520712600632_6255422472318530180_n.jpg?_nc_ht=instagram.fybz2-1.fna.fbcdn.net&_nc_cat=108&_nc_ohc=WQizf6rhDmQAX883HrQ&oh=140f221889178fd03bf654cf18a9d9a2&oe=5F4D2AFE"
filename = image_url.split("?")[0].split("/")[-1]
# Open the url image, set stream to True, this will return the stream content.
r = requests.get(image_url, stream=True)
# Check if the image was retrieved successfully
if r.status_code == 200:
# Set decode_content value to True, otherwise the downloaded image file's size will be zero.
r.raw.decode_content = True
# Open a local file with wb ( write binary ) permission.
with open(filename, 'wb') as f:
shutil.copyfileobj(r.raw, f)
print('Image sucessfully Downloaded: ', filename)
else:
print('Image Couldn\'t be retreived')
What I am trying to do is loop through a list of URL to download a series of .pdfs, and save them to a .zip. At the moment I am just trying to test code using just one URL. The ERROR I am getting is:
Traceback (most recent call last):
File "I:\test_pdf_download_zip.py", line 36, in <module>
zip_file(zipfile_name, url)
File "I:\test_pdf_download_zip.py", line 30, in zip_file
myzip.write(dowload_pdf(url))
TypeError: expected a string or other character buffer object
Would someone know how to pass .pdf request to the .zip correctly (avoiding the error above) in order for me to append it, or know if it is possible to do this?
import os
import zipfile
import requests
output = r"I:"
# File name of the zipfile
zipfile_name = os.path.join(output, "test.zip")
# Random test pdf
url = r"http://www.pdf995.com/samples/pdf.pdf"
def create_zipfile(zipfile_name):
zipfile.ZipFile(zipfile_name, "w")
def dowload_pdf(url):
response = requests.get(url, stream=True)
with open('test.pdf', 'wb') as f:
f.write(response.content)
def zip_file(zip_name, url):
with open(zip_name,'a') as myzip:
myzip.write(dowload_pdf(url))
if __name__ == "__main__":
create_zipfile(zipfile_name)
zip_file(zipfile_name, url)
print("Done")
Your download_pdf() function is saving a file but it doesn't return anything. You need to modify it so it actually returns the file path to myzip.write(). You don't want to hardcode test.pdf but pass unique paths to your download function so you don't end up with multiple test.pdf in your archive.
def dowload_pdf(url, path):
response = requests.get(url, stream=True)
with open(path, 'wb') as f:
f.write(response.content)
return path
I really like how I can easily share files on a network using the SimpleHTTPServer, but I wish there was an option like "download entire directory". Is there an easy (one liner) way to implement this?
Thanks
I did that modification for you, I don't know if there'are better ways to do that but:
Just save the file (Ex.: ThreadedHTTPServer.py) and access as:
$ python -m /path/to/ThreadedHTTPServer PORT
BPaste Raw Version
The modification also works in threaded way so you won't have problem with download and navigation in the same time, the code aren't organized but:
from BaseHTTPServer import HTTPServer, BaseHTTPRequestHandler
from SocketServer import ThreadingMixIn
import threading
import SimpleHTTPServer
import sys, os, zipfile
PORT = int(sys.argv[1])
def send_head(self):
"""Common code for GET and HEAD commands.
This sends the response code and MIME headers.
Return value is either a file object (which has to be copied
to the outputfile by the caller unless the command was HEAD,
and must be closed by the caller under all circumstances), or
None, in which case the caller has nothing further to do.
"""
path = self.translate_path(self.path)
f = None
if self.path.endswith('?download'):
tmp_file = "tmp.zip"
self.path = self.path.replace("?download","")
zip = zipfile.ZipFile(tmp_file, 'w')
for root, dirs, files in os.walk(path):
for file in files:
if os.path.join(root, file) != os.path.join(root, tmp_file):
zip.write(os.path.join(root, file))
zip.close()
path = self.translate_path(tmp_file)
elif os.path.isdir(path):
if not self.path.endswith('/'):
# redirect browser - doing basically what apache does
self.send_response(301)
self.send_header("Location", self.path + "/")
self.end_headers()
return None
else:
for index in "index.html", "index.htm":
index = os.path.join(path, index)
if os.path.exists(index):
path = index
break
else:
return self.list_directory(path)
ctype = self.guess_type(path)
try:
# Always read in binary mode. Opening files in text mode may cause
# newline translations, making the actual size of the content
# transmitted *less* than the content-length!
f = open(path, 'rb')
except IOError:
self.send_error(404, "File not found")
return None
self.send_response(200)
self.send_header("Content-type", ctype)
fs = os.fstat(f.fileno())
self.send_header("Content-Length", str(fs[6]))
self.send_header("Last-Modified", self.date_time_string(fs.st_mtime))
self.end_headers()
return f
def list_directory(self, path):
try:
from cStringIO import StringIO
except ImportError:
from StringIO import StringIO
import cgi, urllib
"""Helper to produce a directory listing (absent index.html).
Return value is either a file object, or None (indicating an
error). In either case, the headers are sent, making the
interface the same as for send_head().
"""
try:
list = os.listdir(path)
except os.error:
self.send_error(404, "No permission to list directory")
return None
list.sort(key=lambda a: a.lower())
f = StringIO()
displaypath = cgi.escape(urllib.unquote(self.path))
f.write('<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">')
f.write("<html>\n<title>Directory listing for %s</title>\n" % displaypath)
f.write("<body>\n<h2>Directory listing for %s</h2>\n" % displaypath)
f.write("<a href='%s'>%s</a>\n" % (self.path+"?download",'Download Directory Tree as Zip'))
f.write("<hr>\n<ul>\n")
for name in list:
fullname = os.path.join(path, name)
displayname = linkname = name
# Append / for directories or # for symbolic links
if os.path.isdir(fullname):
displayname = name + "/"
linkname = name + "/"
if os.path.islink(fullname):
displayname = name + "#"
# Note: a link to a directory displays with # and links with /
f.write('<li>%s\n'
% (urllib.quote(linkname), cgi.escape(displayname)))
f.write("</ul>\n<hr>\n</body>\n</html>\n")
length = f.tell()
f.seek(0)
self.send_response(200)
encoding = sys.getfilesystemencoding()
self.send_header("Content-type", "text/html; charset=%s" % encoding)
self.send_header("Content-Length", str(length))
self.end_headers()
return f
Handler = SimpleHTTPServer.SimpleHTTPRequestHandler
Handler.send_head = send_head
Handler.list_directory = list_directory
class ThreadedHTTPServer(ThreadingMixIn, HTTPServer):
"""Handle requests in a separate thread."""
if __name__ == '__main__':
server = ThreadedHTTPServer(('0.0.0.0', PORT), Handler)
print 'Starting server, use <Ctrl-C> to stop'
server.serve_forever()
Look at the sources, e.g. online here. Right now, if you call the server with a URL that's a directory, its index.html file is served, or, missing that, the list_directory method is called. Presumably, you want instead to make a zip file with the directory's contents (recursively, I imagine), and serve that? Obviously there's no way to do it with a one-line change, since you want to replace what are now lines 68-80 (in method send_head) plus the whole of method list_directory, lines 98-137 -- that's already at least a change to over 50 lines;-).
If you're OK with a change of several dozen lines, not one, and the semantics I've described are what you want, you could of course build the required zipfile as a cStringIO.StringIO object with the ZipFile class, and populate it with an os.walk on the directory in question (assuming you want, recursively, to get all subdirectories as well). But it's most definitely not going to be a one-liner;-).
There is no one liner which would do it, also what do you mean by "download whole dir" as tar or zip?
Anyway you can follow these steps
Derive a class from SimpleHTTPRequestHandler or may be just copy its code
Change list_directory method to return a link to "download whole folder"
Change copyfile method so that for your links you zip whole dir and return it
You may cache zip so that you do not zip folder every time, instead see if any file is modified or not
Would be a fun exercise to do :)
There is no simple way.
An alternative is to use the python script below to download the whole folder recursively. This works well for Python 3. Change the URL as needed.
import os
from pathlib import Path
from urllib.parse import urlparse, urljoin
import requests
from bs4 import BeautifulSoup
def get_links(content):
soup = BeautifulSoup(content)
for a in soup.findAll('a'):
yield a.get('href')
def download(url):
path = urlparse(url).path.lstrip('/')
print(path)
r = requests.get(url)
if r.status_code != 200:
raise Exception('status code is {} for {}'.format(r.status_code, url))
content = r.text
if path.endswith('/'):
Path(path.rstrip('/')).mkdir(parents=True, exist_ok=True)
for link in get_links(content):
if not link.startswith('.'): # skip hidden files such as .DS_Store
download(urljoin(url, link))
else:
with open(path, 'w') as f:
f.write(content)
if __name__ == '__main__':
# the trailing / indicates a folder
url = 'http://ed470d37.ngrok.io/a/bc/'
download(url)
I like #mononoke 's solution. But there are several problems in it. They are
write files in text mode
sometimeshref and text are different, especially for non-ascii path
not download large file block-wisely
I tried to fix these problems：
import os
from pathlib import Path
from urllib.parse import urlparse, urljoin
import requests
from bs4 import BeautifulSoup
import math
def get_links(content):
soup = BeautifulSoup(content)
for a in soup.findAll('a'):
yield a.get('href'), a.get_text()
def download(url, path=None, overwrite=False):
if path is None:
path = urlparse(url).path.lstrip('/')
if url.endswith('/'):
r = requests.get(url)
if r.status_code != 200:
raise Exception('status code is {} for {}'.format(r.status_code, url))
content = r.text
Path(path.rstrip('/')).mkdir(parents=True, exist_ok=True)
for link, name in get_links(content):
if not link.startswith('.'): # skip hidden files such as .DS_Store
download(urljoin(url, link), os.path.join(path, name))
else:
if os.path.isfile(path):
print("#existing", path)
if not overwrite:
return
chunk_size = 1024*1024
r = requests.get(url, stream=True)
content_size = int(r.headers['content-length'])
total = math.ceil(content_size / chunk_size)
print("#", path)
with open(path, 'wb') as f:
c = 0
st = 100
for chunk in r.iter_content(chunk_size=chunk_size):
c += 1
if chunk:
f.write(chunk)
ap = int(c*st/total) - int((c-1)*st/total)
if ap > 0:
print("#" * ap, end="")
print("\r "," "*int(c*st/total), "\r", end="")
if __name__ == '__main__':
# the trailing / indicates a folder
url = 'http://ed470d37.ngrok.io/a/bc/'
download(url, "/data/bc")