Extracting Json Objects from string - python

Lets say I have an incoming string oversocket and it look like this
'text.....text {"foo": {"bar":100}} text {"bar":2} test {"foo"'
What is the best way/library to extract only the json objects out of the incoming string?
I have tried simplejson.JSONDecoder from simple json library. However, it is not only finding objects or I didn't know how to use it.
I have tried something like this so far
import simplejson as json
input_buffer = ""
def in_data(data):
input_buffer += data
try:
dict, idx = json.JSONDecoder().raw_decode(input_buffer)
except:
#handle exception in case nothing found
self.handle_input(dict) #send the dictionary for processing
input_buffer = input_buffer[idx:]

Pure python solution based on simple bracket counting and trying to parse gathered text.
import json
inp = list(r'text {"foo": {"bar":100}} text {"bar":2} test ')
stack = ''
bracket_counter = 0
jsons = []
while inp:
char = inp.pop(0)
if char == '{':
bracket_counter += 1
if bracket_counter:
stack += char
if char == '}':
bracket_counter -= 1
if bracket_counter == 0:
try:
parsed = json.loads(stack)
jsons.append(parsed)
except json.JSONDecodeError:
pass
stack = ''
print(jsons) # -> [{'foo': {'bar': 100}}, {'bar': 2}]

Related

I want to remove the unwanted sub-level duplicate tags using lxml etree

This is the input sample text. I want to do in object based cleanup to avoid hierarchy issues
<p><b><b><i><b><i><b>
<i>sample text</i>
</b></i></b></i></b></b></p>
Required Output
<p><b><i>sample text</i></b></p>
I written this Object based cleanup using lxml for sublevel duplicate tags. It may help others.
import lxml.etree as ET
textcont = '<p><b><b><i><b><i><b><i>sample text</i></b></i></b></i></b></b></p>'
soup = ET.fromstring(textcont)
for tname in ['i','b']:
for tagn in soup.iter(tname):
if tagn.getparent().getparent() != None and tagn.getparent().getparent().tag == tname:
iparOfParent = tagn.getparent().getparent()
iParent = tagn.getparent()
if iparOfParent.text == None:
iparOfParent.addnext(iParent)
iparOfParent.getparent().remove(iparOfParent)
elif tagn.getparent() != None and tagn.getparent().tag == tname:
iParent = tagn.getparent()
if iParent.text == None:
iParent.addnext(tagn)
iParent.getparent().remove(iParent)
print(ET.tostring(soup))
output:
b'<p><b><i>sample text</i></b></p>'
Markdown, itself, provides structural to extract elements inside
Using re in python, you may extract elements and recombine them.
For example:
import re
html = """<p><b><b><i><b><i><b>
<i>sample text</i>
</b></i></b></i></b></b></p>"""
regex_object = re.compile("\<(.*?)\>")
html_objects = regex_object.findall(html)
set_html = []
for obj in html_objects:
if obj[0] != "/" and obj not in set_html:
set_html.append(obj)
regex_text = re.compile("\>(.*?)\<")
text = [result for result in regex_text.findall(html) if result][0]
# Recombine
result = ""
for obj in set_html:
result += f"<{obj}>"
result += text
for obj in set_html[::-1]:
result += f"</{obj}>"
# result = '<p><b><i>sample text</i></b></p>'
You can use the regex library re to create a function to search for the matching opening tag and closing tag pair and everything else in between. Storing tags in a dictionary will remove duplicate tags and maintain the order they were found in (if order isn't important then just use a set). Once all pairs of tags are found, wrap what's left with the keys of the dictionary in reverse order.
import re
def remove_duplicates(string):
tags = {}
while (match := re.findall(r'\<(.+)\>([\w\W]*)\<\/\1\>', string)):
tag, string = match[0][0], match[0][1] # match is [(group0, group1)]
tags.update({tag: None})
for tag in reversed(tags):
string = f'<{tag}>{string}</{tag}>'
return string
Note: I've used [\w\W]* as a cheat to match everything.

Parsing Json with multiple "levels" with Python

I'm trying to parse a json file from an api call.
I have found this code that fits my need and trying to adapt it to what I want:
import math, urllib2, json, re
def download():
graph = {}
page = urllib2.urlopen("http://fx.priceonomics.com/v1/rates/?q=1")
jsrates = json.loads(page.read())
pattern = re.compile("([A-Z]{3})_([A-Z]{3})")
for key in jsrates:
matches = pattern.match(key)
conversion_rate = -math.log(float(jsrates[key]))
from_rate = matches.group(1).encode('ascii','ignore')
to_rate = matches.group(2).encode('ascii','ignore')
if from_rate != to_rate:
if from_rate not in graph:
graph[from_rate] = {}
graph[from_rate][to_rate] = float(conversion_rate)
return graph
And I've turned it into:
import math, urllib2, json, re
def download():
graph = {}
page = urllib2.urlopen("https://bittrex.com/api/v1.1/public/getmarketsummaries")
jsrates = json.loads(page.read())
for pattern in jsrates['result'][0]['MarketName']:
for key in jsrates['result'][0]['Ask']:
matches = pattern.match(key)
conversion_rate = -math.log(float(jsrates[key]))
from_rate = matches.group(1).encode('ascii','ignore')
to_rate = matches.group(2).encode('ascii','ignore')
if from_rate != to_rate:
if from_rate not in graph:
graph[from_rate] = {}
graph[from_rate][to_rate] = float(conversion_rate)
return graph
Now the problem is that there is multiple level in the json "Result > 0, 1,2 etc"
json screenshot
for key in jsrates['result'][0]['Ask']:
I want the zero to be able to be any number, I don't know if thats clear.
So I could get all the ask price to match their marketname.
I have shortened the code so it doesnt make too long of a post.
Thanks
PS: sorry for the english, its not my native language.
You could loop through all of the result values that are returned, ignoring the meaningless numeric index:
for result in jsrates['result'].values():
ask = result.get('Ask')
if ask is not None:
# Do things with your ask...

parsing a string in python for #hashtag

I am wondering, how could I make an algorithm that parses a string for the hashtag symbol ' # ' and returns the full string, but where ever a word starts with a '#' symbol, it becomes a link. I am using python with Google app engine: webapp2 and Jinja2 and I am building a blog.
Thanks
A more efficient and complete way to find the "hashwords":
import functools
def hash_position(string):
return string.find('#')
def delimiter_position(string, delimiters):
positions = filter(lambda x: x >= 0, map(lambda delimiter: string.find(delimiter), delimiters))
try:
return functools.reduce(min, positions)
except TypeError:
return -1
def get_hashed_words(string, delimiters):
maximum_length = len(string)
current_hash_position = hash_position(string)
string = string[current_hash_position:]
results = []
counter = 0
while current_hash_position != -1:
current_delimiter_position = delimiter_position(string, delimiters)
if current_delimiter_position == -1:
results.append(string)
else:
results.append(string[0:current_delimiter_position])
# Update offsets and the haystack
string = string[current_delimiter_position:]
current_hash_position = hash_position(string)
string = string[current_hash_position:]
return results
if __name__ == "__main__":
string = "Please #clarify: What do you #mean with returning somthing as a #link. #herp"
delimiters = [' ', '.', ',', ':']
print(get_hashed_words(string, delimiters))
Imperative code with updates of the haystack looks a little bit ugly but hey, that's what we get for (ab-)using mutable variables.
And I still have no idea what do you mean with "returning something as a link".
Hope that helps.
not sure where do you get the data for the link, but maybe something like:
[('%s' % word) for word in input.split() if word[0]=='#']
Are you talking about twitter? Maybe this?
def get_hashtag_link(hashtag):
if hashtag.startswith("#"):
return '%s' % (hashtag[1:], hashtag)
>>> get_hashtag_link("#stackoverflow")
'#stackoverflow'
It will return None if hashtag is not a hashtag.

Unpickling mid-stream (python)

I am writing scripts to process (very large) files by repeatedly unpickling objects until EOF. I would like to partition the file and have separate processes (in the cloud) unpickle and process separate parts.
However my partitioner is not intelligent, it does not know about the boundaries between pickled objects in the file (since those boundaries depend on the object types being pickled, etc.).
Is there a way to scan a file for a "start pickled object" sentinel? The naive way would be to attempt unpickling at successive byte offsets until an object is successfully pickled, but that yields unexpected errors. It seems that for certain combinations of input, the unpickler falls out of sync and returns nothing for the rest of the file (see code below).
import cPickle
import os
def stream_unpickle(file_obj):
while True:
start_pos = file_obj.tell()
try:
yield cPickle.load(file_obj)
except (EOFError, KeyboardInterrupt):
break
except (cPickle.UnpicklingError, ValueError, KeyError, TypeError, ImportError):
file_obj.seek(start_pos+1, os.SEEK_SET)
if __name__ == '__main__':
import random
from StringIO import StringIO
# create some data
sio = StringIO()
[cPickle.dump(random.random(), sio, cPickle.HIGHEST_PROTOCOL) for _ in xrange(1000)]
sio.flush()
# read from subsequent offsets and find discontinuous jumps in object count
size = sio.tell()
last_count = None
for step in xrange(size):
sio.seek(step, os.SEEK_SET)
count = sum(1 for _ in stream_unpickle(file_obj))
if last_count is None or count == last_count - 1:
last_count = count
elif count != last_count:
# if successful, these should never print (but they do...)
print '%d elements read from byte %d' % (count, step)
print '(%d elements read from byte %d)' % (last_count, step-1)
last_count = count
The pickletools module has a dis function that shows the opcodes. It shows that there is a STOP opcode that you may be scan for:
>>> import pickle, pickletools, StringIO
>>> s = StringIO.StringIO()
>>> pickle.dump('abc', s)
>>> p = s.getvalue()
>>> pickletools.dis(p)
0: S STRING 'abc'
7: p PUT 0
10: . STOP
highest protocol among opcodes = 0
Note, using the STOP opcode is a bit tricky because the codes are of variable length, but it may serve as a useful hint about where the cutoffs are.
If you control the pickling step on the other end, then you can improve the situation by adding your own unambiguous alternative separator:
>>> sep = '\xDE\xAD\xBE\xEF'
>>> s = StringIO.StringIO()
>>> pickle.dump('abc', s)
>>> s.write(sep)
>>> pickle.dump([10, 20], s)
>>> s.write(sep)
>>> pickle.dump('def', s)
>>> s.write(sep)
>>> pickle.dump([30, 40], s)
>>> p = s.getvalue()
Before unpacking, split into separate pickles using the known separator:
>>> for pick in p.split(sep):
print pickle.loads(pick)
abc
[10, 20]
def
[30, 40]
In the pickled file, some opcodes have an argument -- a data value that follows the opcode. The data values vary in length, and can contain bytes identical to opcodes. Therefore, if you start reading the file from an arbitrary position, you have no way of knowing if you are looking at an opcode or in the middle of an argument. You must read the file from beginning and parse the opcodes.
I cooked up this function that skips one pickle from a file, i.e. reads it and parses opcodes, but does not construct the objects. It seems slightly faster than cPickle.loads on some files I have. You could rewrite this in C for more speed. (after testing this properly)
Then, you can make one pass over the whole file to get the seek position of each pickle.
from pickletools import code2op, UP_TO_NEWLINE, TAKEN_FROM_ARGUMENT1, TAKEN_FROM_ARGUMENT4
from marshal import loads as mloads
def skip_pickle(f):
"""Skip one pickle from file.
'f' is a file-like object containing the pickle.
"""
while True:
code = f.read(1)
if not code:
raise EOFError
opcode = code2op[code]
if opcode.arg is not None:
n = opcode.arg.n
if n > 0:
f.read(n)
elif n == UP_TO_NEWLINE:
f.readline()
elif n == TAKEN_FROM_ARGUMENT1:
n = ord(f.read(1))
f.read(n)
elif n == TAKEN_FROM_ARGUMENT4:
n = mloads('i' + f.read(4))
f.read(n)
if code == '.':
break
Sorry to answer my own question, and thanks to #RaymondHettinger for the idea of adding sentinels.
Here's what worked for me. I created readers and writers that use a sentinel '#S' followed by a data block length at the beginning of each 'record'. The writer has to take care to find any occurrences of '#' in the data being written and double them (into '##'). The reader then uses a look-behind regex to find sentinels, distinct from any matching values that might be in the original stream, and also verify the number of bytes between this sentinel and the subsequent one.
RecordWriter is a context manager (so multiple calls to write() can be encapsulated into a single record if needed). RecordReader is a generator.
Not sure how this is on performance. Any faster/elegant-er solutions are welcome.
import re
import cPickle
from functools import partial
from cStringIO import StringIO
SENTINEL = '#S'
# when scanning look for #S, but NOT ##S
sentinel_pattern = '(?<!#)#S' # uses negative look-behind
sentinel_re = re.compile(sentinel_pattern)
find_sentinel = sentinel_re.search
# when writing replace single # with double ##
write_pattern = '#'
write_re = re.compile(write_pattern)
fix_write = partial(write_re.sub, '##')
# when reading, replace double ## with single #
read_pattern = '##'
read_re = re.compile(read_pattern)
fix_read = partial(read_re.sub, '#')
class RecordWriter(object):
def __init__(self, stream):
self._stream = stream
self._write_buffer = None
def __enter__(self):
self._write_buffer = StringIO()
return self
def __exit__(self, et, ex, tb):
if self._write_buffer.tell():
self._stream.write(SENTINEL) # start
cPickle.dump(self._write_buffer.tell(), self._stream, cPickle.HIGHEST_PROTOCOL) # byte length of user's original data
self._stream.write(fix_write(self._write_buffer.getvalue()))
self._write_buffer = None
return False
def write(self, data):
if not self._write_buffer:
raise ValueError("Must use StreamWriter as a context manager")
self._write_buffer.write(data)
class BadBlock(Exception): pass
def verify_length(block):
fobj = StringIO(block)
try:
stated_length = cPickle.load(fobj)
except (ValueError, IndexError, cPickle.UnpicklingError):
raise BadBlock
data = fobj.read()
if len(data) != stated_length:
raise BadBlock
return data
def RecordReader(stream):
' Read one record '
accum = StringIO()
seen_sentinel = False
data = ''
while True:
m = find_sentinel(data)
if not m:
if seen_sentinel:
accum.write(data)
data = stream.read(80)
if not data:
if accum.tell():
try: yield verify_length(fix_read(accum.getvalue()))
except BadBlock: pass
return
else:
if seen_sentinel:
accum.write(data[:m.start()])
try: yield verify_length(fix_read(accum.getvalue()))
except BadBlock: pass
accum = StringIO()
else:
seen_sentinel = True
data = data[m.end():] # toss
if __name__ == '__main__':
import random
stream = StringIO()
data = [str(random.random()) for _ in xrange(3)]
# test with a string containing sentinel and almost-sentinel
data.append('abc12#jeoht38#SoSooihetS#')
count = len(data)
for i in data:
with RecordWriter(stream) as r:
r.write(i)
size = stream.tell()
start_pos = random.random() * size
stream.seek(start_pos, os.SEEK_SET)
read_data = [s for s in RecordReader(stream)]
print 'Original data: ', data
print 'After seeking to %d, RecordReader returned: %s' % (start_pos, read_data)

How to read/make sense of a PHP serialised data string in python

A legacy database I'm accessing via Django has a table column that stores serialised data in the following string format:
a:5:{i:1;s:4:"1869";i:2;s:4:"1859";i:3;s:4:"1715";i:4;s:1:"0";i:5;s:1:"0";}
Is there any way I can use python/python-library to change it into a list or any other friendly python data type for further processing of individual values?
Note: These values were written to the database via PHP.
phpserialize:
a port of the serialize and unserialize functions of php to python. This module implements the python serialization interface (eg: provides dumps, loads and similar functions)...
Here's a very rough and incomplete implementation:
def p(f, d): # parse until
data = []
b = f.read(1)
while b and b != d:
data.append(b)
b = f.read(1)
return b''.join(data)
def parse(f):
if not hasattr(f, 'read'):
import io
try:
f = io.BytesIO(f)
except TypeError:
f = io.BytesIO(f.encode('utf-8'))
typ = f.read(2)
if typ == b'i:':
return int(p(f, b';'))
if typ == b'd:':
return float(p(f, b';'))
if typ == b's:':
return f.read(int(p(f, b':')) + 3)[1:-2].decode('utf-8')
if typ == b'a:':
l = int(p(f, b':'))
f.read(1) # {
items = [(parse(f), parse(f)) for i in range(l)]
f.read(1) # }
return dict(items)
assert False, typ

Categories

Resources