I crawled some webpages using python's urllib.request API and saved the read lines into a new file.
f = open(docId + ".html", "w+")
with urllib.request.urlopen('http://stackoverflow.com') as u:
s = u.read()
f.write(str(s))
But when I open the saved files, I see many strings such as \xe2\x86\x90, which was originally an arrow symbol in the original page. It seems to be a UTF-8 code of the symbol, but how do I convert the code to the symbol back?
Your code is broken: u.read() returns bytes object. str(bytes_object) returns a string representation of the object (how the bytes literal would look like) -- you don't want it here:
>>> str(b'\xe2\x86\x90')
"b'\\xe2\\x86\\x90'"
Either save the bytes on disk as is:
import urllib.request
urllib.request.urlretrieve('http://stackoverflow.com', 'so.html')
or open the file in binary mode: 'wb' and save it manually:
import shutil
from urllib.request import urlopen
with urlopen('http://stackoverflow.com') as u, open('so.html', 'wb') as file:
shutil.copyfileobj(u, file)
or convert bytes to Unicode and save them to disk using any encoding you like.
import io
import shutil
from urllib.request import urlopen
with urlopen('http://stackoverflow.com') as u, \
open('so.html', 'w', encoding='utf-8', newline='') as file, \
io.TextIOWrapper(u, encoding=u.headers.get_content_charset('utf-8'), newline='') as t:
shutil.copyfileobj(t, file)
Try:
import urllib2, io
with io.open("test.html", "w", encoding='utf8') as fout:
s = urllib2.urlopen('http://stackoverflow.com').read()
s = s.decode('utf8', 'ignore') # or s.decode('utf8', 'replace')
fout.write(s)
See https://docs.python.org/2/howto/unicode.html
Related
I would like to do the following in Python 3: Read in a FortranFile, but from an URL rather than a local file. The reason is that for my concrete example there are a lot of files and I want to avoid having to download them all first.
I have managed to
a) read in a simple .txt file from an URL
import urllib
from urllib.request import urlopen
url='http://www.deus-consortium.org/deus-library/filelist/deus_file_list_501.txt'
data=urllib.request.urlopen(url)
i=0
for line in data: # files are iterable
print(i,line)
i+=1
#alternative: data.read()
b) read in a local FortranFile (binary little endian unformated Fortran file) like this:
The file is from: http://www.deus-consortium.org/deus-library/efiler1/Babel_le/boxlen648_n2048_lcdmw7/post/fof/output_00090/fof_boxlen648_n2048_lcdmw7_masst_00000
from scipy.io import FortranFile
filename='../../Downloads/fof_boxlen648_n2048_rpcdmw7_masst_00000'
ff = FortranFile(filename, 'r')
nhalos=ff.read_ints(dtype=np.int32)[0]
print('number of halos in file',nhalos)
Is there any way to avoid downloading and reading FortranFiles directly from the URL? I tried
import urllib
from urllib.request import urlopen
url='http://www.deus-consortium.org/deus-library/efiler1/Babel_le/boxlen648_n2048_lcdmw7/cube_00090/fof_boxlen648_n2048_lcdmw7_cube_00000'
pathname = urllib.request.urlopen(url)
ff = FortranFile(pathname, 'r')
ff.read_ints()
gives "OSError: obtaining file position failed". pathname.read() doesn't work either because it's a fortran file.
Any ideas? Thanks in advance!
Maybe you can use tempfile module to download and read the data?
For example:
import urllib
import tempfile
from scipy.io import FortranFile
from urllib.request import urlopen
url='http://www.deus-consortium.org/deus-library/efiler1/Babel_le/boxlen648_n2048_lcdmw7/cube_00090/fof_boxlen648_n2048_lcdmw7_cube_00000'
with tempfile.TemporaryFile() as fp:
fp.write(urllib.request.urlopen(url).read())
fp.seek(0)
ff = FortranFile(fp, 'r')
info = ff.read_ints()
print(info)
Prints:
[12808737]
I have downloaded a compressed json file and want to open it as a dictionary.
I used json.load but the data type still gives me a string.
I want to extract a keyword list from the json file. Is there a way I can do it even though my data is a string?
Here is my code:
import gzip
import json
with gzip.open("19.04_association_data.json.gz", "r") as f:
data = f.read()
with open('association.json', 'w') as json_file:
json.dump(data.decode('utf-8'), json_file)
with open("association.json", "r") as read_it:
association_data = json.load(read_it)
print(type(association_data))
#The actual output is 'str' but I expect it is 'dic'
In the first with block you already got the uncompressed string, no need to open it a second time.
import gzip
import json
with gzip.open("19.04_association_data.json.gz", "r") as f:
data = f.read()
j = json.loads (data.decode('utf-8'))
print (type(j))
Open the file using the gzip package from the standard library (docs), then read it directly into json.loads():
import gzip
import json
with gzip.open("19.04_association_data.json.gz", "rb") as f:
data = json.loads(f.read(), encoding="utf-8")
To read from a json.gz, you can use the following snippet:
import json
import gzip
with gzip.open("file_path_to_read", "rt") as f:
expected_dict = json.load(f)
The result is of type dict.
In case if you want to write to a json.gz, you can use the following snippet:
import json
import gzip
with gzip.open("file_path_to_write", "wt") as f:
json.dump(expected_dict, f)
I have multiple gzfile in subfolders that I want to unzip in one folder. It works fine but there's a BOM signature at the beginning of each file that I would like to be removed. I have checked other questions like Removing BOM from gzip'ed CSV in Python or Convert UTF-8 with BOM to UTF-8 with no BOM in Python but it doesn't seem to work. I use Python 3.6 in Pycharm on Windows.
Here's first my code without attempt:
import gzip
import pickle
import glob
def save_object(obj, filename):
with open(filename, 'wb') as output: # Overwrites any existing file.
pickle.dump(obj, output, pickle.HIGHEST_PROTOCOL)
output_path = 'path_out'
i = 1
for filename in glob.iglob(
'path_in/**/*.gz', recursive=True):
print(filename)
with gzip.open(filename, 'rb') as f:
file_content = f.read()
new_file = output_path + "z" + str(i) + ".txt"
save_object(file_content, new_file)
f.close()
i += 1
Now, with the logic defined in Removing BOM from gzip'ed CSV in Python (at least what I understand of it) if I replace file_content = f.read() by file_content = csv.reader(f.read().decode('utf-8-sig').encode('utf-8').splitlines()), I get:
TypeError: can't pickle _csv.reader objects
I checked for this error (e.g. "Can't pickle <type '_csv.reader'>" error when using multiprocessing on Windows) but I found no solution I could apply.
A minor adaptation of the very first question you link to trivially works.
tripleee$ cat bomgz.py
import gzip
from subprocess import run
with open('bom.txt', 'w') as handle:
handle.write('\ufeffmoo!\n')
run(['gzip', 'bom.txt'])
with gzip.open('bom.txt.gz', 'rb') as f:
file_content = f.read().decode('utf-8-sig')
with open('nobom.txt', 'w') as output:
output.write(file_content)
tripleee$ python3 bomgz.py
tripleee$ gzip -dc bom.txt.gz | xxd
00000000: efbb bf6d 6f6f 210a ...moo!.
tripleee$ xxd nobom.txt
00000000: 6d6f 6f21 0a moo!.
The pickle parts didn't seem relevant here but might have been obscuring the goal of getting a block of decoded str out of an encoded blob of bytes.
I am trying to download a PDF file from a website and save it to disk. My attempts either fail with encoding errors or result in blank PDFs.
In [1]: import requests
In [2]: url = 'http://www.hrecos.org//images/Data/forweb/HRTVBSH.Metadata.pdf'
In [3]: response = requests.get(url)
In [4]: with open('/tmp/metadata.pdf', 'wb') as f:
...: f.write(response.text)
---------------------------------------------------------------------------
UnicodeEncodeError Traceback (most recent call last)
<ipython-input-4-4be915a4f032> in <module>()
1 with open('/tmp/metadata.pdf', 'wb') as f:
----> 2 f.write(response.text)
3
UnicodeEncodeError: 'ascii' codec can't encode characters in position 11-14: ordinal not in range(128)
In [5]: import codecs
In [6]: with codecs.open('/tmp/metadata.pdf', 'wb', encoding='utf8') as f:
...: f.write(response.text)
...:
I know it is a codec problem of some kind but I can't seem to get it to work.
You should use response.content in this case:
with open('/tmp/metadata.pdf', 'wb') as f:
f.write(response.content)
From the document:
You can also access the response body as bytes, for non-text requests:
>>> r.content
b'[{"repository":{"open_issues":0,"url":"https://github.com/...
So that means: response.text return the output as a string object, use it when you're downloading a text file. Such as HTML file, etc.
And response.content return the output as bytes object, use it when you're downloading a binary file. Such as PDF file, audio file, image, etc.
You can also use response.raw instead. However, use it when the file which you're about to download is large. Below is a basic example which you can also find in the document:
import requests
url = 'http://www.hrecos.org//images/Data/forweb/HRTVBSH.Metadata.pdf'
r = requests.get(url, stream=True)
with open('/tmp/metadata.pdf', 'wb') as fd:
for chunk in r.iter_content(chunk_size):
fd.write(chunk)
chunk_size is the chunk size which you want to use. If you set it as 2000, then requests will download that file the first 2000 bytes, write them into the file, and do this again, again and again, unless it finished.
So this can save your RAM. But I'd prefer use response.content instead in this case since your file is small. As you can see use response.raw is complex.
Relates:
How to download large file in python with requests.py?
How to download image using requests
In Python 3, I find pathlib is the easiest way to do this. Request's response.content marries up nicely with pathlib's write_bytes.
from pathlib import Path
import requests
filename = Path('metadata.pdf')
url = 'http://www.hrecos.org//images/Data/forweb/HRTVBSH.Metadata.pdf'
response = requests.get(url)
filename.write_bytes(response.content)
You can use urllib:
import urllib.request
urllib.request.urlretrieve(url, "filename.pdf")
Please note I'm a beginner. If My solution is wrong, please feel free to correct and/or let me know. I may learn something new too.
My solution:
Change the downloadPath accordingly to where you want your file to be saved. Feel free to use the absolute path too for your usage.
Save the below as downloadFile.py.
Usage: python downloadFile.py url-of-the-file-to-download new-file-name.extension
Remember to add an extension!
Example usage: python downloadFile.py http://www.google.co.uk google.html
import requests
import sys
import os
def downloadFile(url, fileName):
with open(fileName, "wb") as file:
response = requests.get(url)
file.write(response.content)
scriptPath = sys.path[0]
downloadPath = os.path.join(scriptPath, '../Downloads/')
url = sys.argv[1]
fileName = sys.argv[2]
print('path of the script: ' + scriptPath)
print('downloading file to: ' + downloadPath)
downloadFile(url, downloadPath + fileName)
print('file downloaded...')
print('exiting program...')
Generally, this should work in Python3:
import urllib.request
..
urllib.request.get(url)
Remember that urllib and urllib2 don't work properly after Python2.
If in some mysterious cases requests don't work (happened with me), you can also try using
wget.download(url)
Related:
Here's a decent explanation/solution to find and download all pdf files on a webpage:
https://medium.com/#dementorwriter/notesdownloader-use-web-scraping-to-download-all-pdfs-with-python-511ea9f55e48
regarding Kevin answer to write in a folder tmp, it should be like this:
with open('./tmp/metadata.pdf', 'wb') as f:
f.write(response.content)
he forgot . before the address and of-course your folder tmp should have been created already
I have managed to get my first python script to work which downloads a list of .ZIP files from a URL and then proceeds to extract the ZIP files and writes them to disk.
I am now at a loss to achieve the next step.
My primary goal is to download and extract the zip file and pass the contents (CSV data) via a TCP stream. I would prefer not to actually write any of the zip or extracted files to disk if I could get away with it.
Here is my current script which works but unfortunately has to write the files to disk.
import urllib, urllister
import zipfile
import urllib2
import os
import time
import pickle
# check for extraction directories existence
if not os.path.isdir('downloaded'):
os.makedirs('downloaded')
if not os.path.isdir('extracted'):
os.makedirs('extracted')
# open logfile for downloaded data and save to local variable
if os.path.isfile('downloaded.pickle'):
downloadedLog = pickle.load(open('downloaded.pickle'))
else:
downloadedLog = {'key':'value'}
# remove entries older than 5 days (to maintain speed)
# path of zip files
zipFileURL = "http://www.thewebserver.com/that/contains/a/directory/of/zip/files"
# retrieve list of URLs from the webservers
usock = urllib.urlopen(zipFileURL)
parser = urllister.URLLister()
parser.feed(usock.read())
usock.close()
parser.close()
# only parse urls
for url in parser.urls:
if "PUBLIC_P5MIN" in url:
# download the file
downloadURL = zipFileURL + url
outputFilename = "downloaded/" + url
# check if file already exists on disk
if url in downloadedLog or os.path.isfile(outputFilename):
print "Skipping " + downloadURL
continue
print "Downloading ",downloadURL
response = urllib2.urlopen(downloadURL)
zippedData = response.read()
# save data to disk
print "Saving to ",outputFilename
output = open(outputFilename,'wb')
output.write(zippedData)
output.close()
# extract the data
zfobj = zipfile.ZipFile(outputFilename)
for name in zfobj.namelist():
uncompressed = zfobj.read(name)
# save uncompressed data to disk
outputFilename = "extracted/" + name
print "Saving extracted file to ",outputFilename
output = open(outputFilename,'wb')
output.write(uncompressed)
output.close()
# send data via tcp stream
# file successfully downloaded and extracted store into local log and filesystem log
downloadedLog[url] = time.time();
pickle.dump(downloadedLog, open('downloaded.pickle', "wb" ))
Below is a code snippet I used to fetch zipped csv file, please have a look:
Python 2:
from StringIO import StringIO
from zipfile import ZipFile
from urllib import urlopen
resp = urlopen("http://www.test.com/file.zip")
myzip = ZipFile(StringIO(resp.read()))
for line in myzip.open(file).readlines():
print line
Python 3:
from io import BytesIO
from zipfile import ZipFile
from urllib.request import urlopen
# or: requests.get(url).content
resp = urlopen("http://www.test.com/file.zip")
myzip = ZipFile(BytesIO(resp.read()))
for line in myzip.open(file).readlines():
print(line.decode('utf-8'))
Here file is a string. To get the actual string that you want to pass, you can use zipfile.namelist(). For instance,
resp = urlopen('http://mlg.ucd.ie/files/datasets/bbc.zip')
myzip = ZipFile(BytesIO(resp.read()))
myzip.namelist()
# ['bbc.classes', 'bbc.docs', 'bbc.mtx', 'bbc.terms']
My suggestion would be to use a StringIO object. They emulate files, but reside in memory. So you could do something like this:
# get_zip_data() gets a zip archive containing 'foo.txt', reading 'hey, foo'
import zipfile
from StringIO import StringIO
zipdata = StringIO()
zipdata.write(get_zip_data())
myzipfile = zipfile.ZipFile(zipdata)
foofile = myzipfile.open('foo.txt')
print foofile.read()
# output: "hey, foo"
Or more simply (apologies to Vishal):
myzipfile = zipfile.ZipFile(StringIO(get_zip_data()))
for name in myzipfile.namelist():
[ ... ]
In Python 3 use BytesIO instead of StringIO:
import zipfile
from io import BytesIO
filebytes = BytesIO(get_zip_data())
myzipfile = zipfile.ZipFile(filebytes)
for name in myzipfile.namelist():
[ ... ]
I'd like to offer an updated Python 3 version of Vishal's excellent answer, which was using Python 2, along with some explanation of the adaptations / changes, which may have been already mentioned.
from io import BytesIO
from zipfile import ZipFile
import urllib.request
url = urllib.request.urlopen("http://www.unece.org/fileadmin/DAM/cefact/locode/loc162txt.zip")
with ZipFile(BytesIO(url.read())) as my_zip_file:
for contained_file in my_zip_file.namelist():
# with open(("unzipped_and_read_" + contained_file + ".file"), "wb") as output:
for line in my_zip_file.open(contained_file).readlines():
print(line)
# output.write(line)
Necessary changes:
There's no StringIO module in Python 3 (it's been moved to io.StringIO). Instead, I use io.BytesIO]2, because we will be handling a bytestream -- Docs, also this thread.
urlopen:
"The legacy urllib.urlopen function from Python 2.6 and earlier has been discontinued; urllib.request.urlopen() corresponds to the old urllib2.urlopen.", Docs and this thread.
Note:
In Python 3, the printed output lines will look like so: b'some text'. This is expected, as they aren't strings - remember, we're reading a bytestream. Have a look at Dan04's excellent answer.
A few minor changes I made:
I use with ... as instead of zipfile = ... according to the Docs.
The script now uses .namelist() to cycle through all the files in the zip and print their contents.
I moved the creation of the ZipFile object into the with statement, although I'm not sure if that's better.
I added (and commented out) an option to write the bytestream to file (per file in the zip), in response to NumenorForLife's comment; it adds "unzipped_and_read_" to the beginning of the filename and a ".file" extension (I prefer not to use ".txt" for files with bytestrings). The indenting of the code will, of course, need to be adjusted if you want to use it.
Need to be careful here -- because we have a byte string, we use binary mode, so "wb"; I have a feeling that writing binary opens a can of worms anyway...
I am using an example file, the UN/LOCODE text archive:
What I didn't do:
NumenorForLife asked about saving the zip to disk. I'm not sure what he meant by it -- downloading the zip file? That's a different task; see Oleh Prypin's excellent answer.
Here's a way:
import urllib.request
import shutil
with urllib.request.urlopen("http://www.unece.org/fileadmin/DAM/cefact/locode/2015-2_UNLOCODE_SecretariatNotes.pdf") as response, open("downloaded_file.pdf", 'w') as out_file:
shutil.copyfileobj(response, out_file)
I'd like to add my Python3 answer for completeness:
from io import BytesIO
from zipfile import ZipFile
import requests
def get_zip(file_url):
url = requests.get(file_url)
zipfile = ZipFile(BytesIO(url.content))
files = [zipfile.open(file_name) for file_name in zipfile.namelist()]
return files.pop() if len(files) == 1 else files
write to a temporary file which resides in RAM
it turns out the tempfile module ( http://docs.python.org/library/tempfile.html ) has just the thing:
tempfile.SpooledTemporaryFile([max_size=0[,
mode='w+b'[, bufsize=-1[, suffix=''[,
prefix='tmp'[, dir=None]]]]]])
This
function operates exactly as
TemporaryFile() does, except that data
is spooled in memory until the file
size exceeds max_size, or until the
file’s fileno() method is called, at
which point the contents are written
to disk and operation proceeds as with
TemporaryFile().
The resulting file has one additional
method, rollover(), which causes the
file to roll over to an on-disk file
regardless of its size.
The returned object is a file-like
object whose _file attribute is either
a StringIO object or a true file
object, depending on whether
rollover() has been called. This
file-like object can be used in a with
statement, just like a normal file.
New in version 2.6.
or if you're lazy and you have a tmpfs-mounted /tmp on Linux, you can just make a file there, but you have to delete it yourself and deal with naming
Adding on to the other answers using requests:
# download from web
import requests
url = 'http://mlg.ucd.ie/files/datasets/bbc.zip'
content = requests.get(url)
# unzip the content
from io import BytesIO
from zipfile import ZipFile
f = ZipFile(BytesIO(content.content))
print(f.namelist())
# outputs ['bbc.classes', 'bbc.docs', 'bbc.mtx', 'bbc.terms']
Use help(f) to get more functions details for e.g. extractall() which extracts the contents in zip file which later can be used with with open.
All of these answers appear too bulky and long. Use requests to shorten the code, e.g.:
import requests, zipfile, io
r = requests.get(zip_file_url)
z = zipfile.ZipFile(io.BytesIO(r.content))
z.extractall("/path/to/directory")
Vishal's example, however great, confuses when it comes to the file name, and I do not see the merit of redefing 'zipfile'.
Here is my example that downloads a zip that contains some files, one of which is a csv file that I subsequently read into a pandas DataFrame:
from StringIO import StringIO
from zipfile import ZipFile
from urllib import urlopen
import pandas
url = urlopen("https://www.federalreserve.gov/apps/mdrm/pdf/MDRM.zip")
zf = ZipFile(StringIO(url.read()))
for item in zf.namelist():
print("File in zip: "+ item)
# find the first matching csv file in the zip:
match = [s for s in zf.namelist() if ".csv" in s][0]
# the first line of the file contains a string - that line shall de ignored, hence skiprows
df = pandas.read_csv(zf.open(match), low_memory=False, skiprows=[0])
(Note, I use Python 2.7.13)
This is the exact solution that worked for me. I just tweaked it a little bit for Python 3 version by removing StringIO and adding IO library
Python 3 Version
from io import BytesIO
from zipfile import ZipFile
import pandas
import requests
url = "https://www.nseindia.com/content/indices/mcwb_jun19.zip"
content = requests.get(url)
zf = ZipFile(BytesIO(content.content))
for item in zf.namelist():
print("File in zip: "+ item)
# find the first matching csv file in the zip:
match = [s for s in zf.namelist() if ".csv" in s][0]
# the first line of the file contains a string - that line shall de ignored, hence skiprows
df = pandas.read_csv(zf.open(match), low_memory=False, skiprows=[0])
It wasn't obvious in Vishal's answer what the file name was supposed to be in cases where there is no file on disk. I've modified his answer to work without modification for most needs.
from StringIO import StringIO
from zipfile import ZipFile
from urllib import urlopen
def unzip_string(zipped_string):
unzipped_string = ''
zipfile = ZipFile(StringIO(zipped_string))
for name in zipfile.namelist():
unzipped_string += zipfile.open(name).read()
return unzipped_string
Use the zipfile module. To extract a file from a URL, you'll need to wrap the result of a urlopen call in a BytesIO object. This is because the result of a web request returned by urlopen doesn't support seeking:
from urllib.request import urlopen
from io import BytesIO
from zipfile import ZipFile
zip_url = 'http://example.com/my_file.zip'
with urlopen(zip_url) as f:
with BytesIO(f.read()) as b, ZipFile(b) as myzipfile:
foofile = myzipfile.open('foo.txt')
print(foofile.read())
If you already have the file downloaded locally, you don't need BytesIO, just open it in binary mode and pass to ZipFile directly:
from zipfile import ZipFile
zip_filename = 'my_file.zip'
with open(zip_filename, 'rb') as f:
with ZipFile(f) as myzipfile:
foofile = myzipfile.open('foo.txt')
print(foofile.read().decode('utf-8'))
Again, note that you have to open the file in binary ('rb') mode, not as text or you'll get a zipfile.BadZipFile: File is not a zip file error.
It's good practice to use all these things as context managers with the with statement, so that they'll be closed properly.