def convert(self):
document_body = self._prepare_document()
with codecs.open(self.target_name, 'w+') as target:
self.writer = UnicodeWriter(target, FIELDNAMES)
self._write_header_row()
for outline in document_body:
self.process_element(outline)
def convert_opml_to_csv(args):
"""Convert OPML file to Todoist CSV."""
tree = ET.parse(args.file)
opml = tree.getroot()
body = opml.find('body')
with codecs.open(target_name(args.file, 'csv'), 'w+') as target:
writer = UnicodeWriter(target, FIELDNAMES)
writer.writerow(FIELDNAMES)
def make_row(type='', content='', indent = ''):
return [type, content, '', indent, '', '', '', '']
def process_element(outline, level=1):
# content
row = make_row(TYPE_TASK, outline.get('text'), str(level))
writer.writerow(row)
# note
note = outline.get(NOTE_ATTRIB)
if note:
row = make_row(TYPE_NOTE, note)
writer.writerow(row)
# separator
writer.writerow(make_row())
for subelement in outline.findall('outline'):
process_element(subelement, level+1)
for outline in body:
process_element(outline)
def dataset(query_arguments, type_output='csv', delimiter='|', output=stdout, lang=None):
if set(['main', 'union', 'optional', 'filter']) <= set(query_arguments):
query_arguments = format_query(query=query_arguments, lang=lang)
query = factory(main=query_arguments['main'], union=query_arguments['union'],
optional=query_arguments['optional'], filter=query_arguments['filter'])
results = retrieve_result(query)
properties_set = set()
formatted_result = defaultdict(lambda: defaultdict( lambda: defaultdict(lambda: defaultdict(list))))
for result in results:
quantity_of_interest = result['quantity_of_interest']['value']
property_uri = result['property']['value']
property_label = 'property_label' in result and result['property_label']['value'] or ''
hasValue_uri = result['hasValue']['value']
hasValue_label = 'hasValue_label' in result and result['hasValue_label']['value'] or ''
properties_set.add((property_uri, property_label))
formatted_result[quantity_of_interest][property_uri]['hasValue']['hasValue_label'].append(hasValue_label)
formatted_result[quantity_of_interest][property_uri]['hasValue']['hasValue_uri'].append(hasValue_uri)
keys = list(properties_set)
if type_output == 'csv':
out = UnicodeWriter(output, ';')
out.writerow(filter(None, (chain.from_iterable(keys))))
for qoi in formatted_result:
cells = [['%s' % delimiter.join(formatted_result[qoi][key[0]]['hasValue']['hasValue_uri']),
'%s' % delimiter.join(formatted_result[qoi][key[0]]['hasValue']['hasValue_label'])]
if key[1] else ['%s' % delimiter.join(formatted_result[qoi][key[0]]['hasValue']['hasValue_uri'])] for key in keys]
out.writerow(chain.from_iterable(cells))
return formatted_result
def write_json_to_csv(json_list, filename):
from unicode_csv import UnicodeWriter
translate = {
"class_nbr":"course_num",
"crn":"course_num",
"num":"course_num",
"number":"department_num",
"dist":"distribution",
"div":"division",
"lim":"course_cap",
"graded_sem":"seminar",
"graded_seminar":"seminar",
"double_graded_seminar":"seminar",
"dept_name":"department",
}
scrap = {"req", "sign", "note", "prerequisite", "prereq"}
# Get all the available headers.
header_set = {header for obj in json_list for header in obj.keys()}
headers = [h for h in header_set if not (h in translate or h in scrap)]
headers.extend(translate.values())
headers = map(unicode, headers)
headers = list(set(headers))
headers.sort()
with open(filename, "w") as f:
# Prepare the csv.
writer = UnicodeWriter(f)
# Write "cleaned" headers to the CSV
cleaned_headers = [unicode(h.replace(" ","_").lower()) for h in headers]
writer.writerow(cleaned_headers)
for obj in json_list:
for key in translate.keys():
if key in obj:
new_key = translate[key]
obj[new_key] = obj[key]
vals = []
for header in headers:
val = obj.get(header, "")
if type(val) == list:
val = map(str, val)
vals.append(unicode(val))
writer.writerow(vals)
class SqlExportFileWriter(object):
"""Writes rows to a CSV file, optionally filtering on a predicate."""
def __init__(self, dest, predicate=None, use_unicode=False):
if use_unicode:
self._writer = UnicodeWriter(dest, delimiter=DELIMITER)
else:
self._writer = csv.writer(dest, delimiter=DELIMITER)
self._predicate = predicate
def write_header(self, keys):
self._writer.writerow(keys)
def write_rows(self, results):
if self._predicate:
results = [result for result in results if self._predicate(result)]
if results:
self._writer.writerows(results)
def write_to_csv(file_name):
documents = get_docs()
print `documents.count()`
serialized_documents = json.loads(dumps(documents))
csv_file = open(file_name,'w')
csv_writer = UnicodeWriter(csv_file, dialect='excel')
count = 0
for doc in serialized_documents:
print `doc`
del(doc['_id'])
if count == 0:
header = doc.keys()
#header.sort()
csv_writer.writerow(header)
count = count+1
csv_writer.writerow(doc.values())
csv_file.close()
def marcanalyse(files, sample_length=5):
"""
returns a csv of marc keys and analysed values, showing, for example, how many records exist.
================= ==============================================================
Column Description
================= ==============================================================
``tag`` The 3-digit MARC tag.
``subfield`` The single-character subfield.
``tag_meaning`` The English meaning of the tag/subfield, if known.
``record_count`` The number of records that have at least one of these tags.
``min_valency`` The minimum number of this tag or subfield that each record has.
``max_valency`` The maximum number of this tag or subfield that each record has.
``samples`` Non-repeating sample values of the values of each tag or subfield.
================= ==============================================================
"""
analysis = multifile_iter_records(files, sample_length = sample_length)
csv_header=("tag", "subfield", "tag_meaning", "record_count", "min_valency", "max_valency","samples")
writer = UnicodeWriter(sys.stdout)
writer.writerow(csv_header)
listanalysis = [x for x in analysis.iteritems()]
listanalysis.sort()
for key, value in listanalysis:
v = []
v.append(u'"%s"' % key) #tag
v.append(u"") # subfield
v.append(meaning(key)) #tag_meaning
v.append(unicode(value['count'])) #record_count
v.append(unicode(value['min_valency']))
v.append(unicode(value['max_valency']))
v.append(u"\r\r".join(value['samples']))
writer.writerow(v)
listanalysis = [x for x in value['subfields'].iteritems()]
listanalysis.sort()
for subfield, value in listanalysis:
v = []
v.append("") #tag
v.append(subfield) # subfield
v.append(meaning(key, subfield)) #tag_meaning
v.append(unicode(value['count'])) #record_count
v.append(unicode(value['min_valency']))
v.append(unicode(value['max_valency']))
v.append(u"\r\r".join(value['samples']))
writer.writerow(v)
def all_csv():
pseudofile = StringIO()
spamwriter = UnicodeWriter(pseudofile, encoding='utf-8') #, delimiter=' ', quotechar='|', quoting=csv.QUOTE_MINIMAL)
header = ','.join([
'company.name',
'company.cvr',
'context.year',
'grossprofitloss',
])
for company in all_companies:
for context in company.contexts:
if 'grossprofitloss' in context.fields:
spamwriter.writerow([
company.name,
company.cvr,
context.year,
context.fields['grossprofitloss'],
])
return Response(header + '\n' + pseudofile.getvalue(), mimetype='text/csv')
def main():
writer = UnicodeWriter(sys.stdout)
writer.writerow(["gemeente", "stembureau", "postcode", "stemmen"])
for file_path in get_file_paths():
rows = parse_eml_file(file_path)
writer.writerows(rows)
return 0
def on_data(self, data):
raw_data = json.loads(data)
user = {'screen_name': raw_data['user']['screen_name']}
tweet = {'text': processText(raw_data['text'])}
output = open('dados.csv', 'a')
UnicodeWriter(output, delimiter='|', lineterminator='\n').writerow(
(tweet['text'].replace('\n',
' ').replace('r',
' '), user['screen_name']))
output.close()
print('@' + user['screen_name'] + '\n' + tweet['text'] + '\n')
return (True)
def generate_csv(params, sort_by):
class_dict = get_class_dict()
primary_column_name = get_primary_column_name()
all_classes = get_all_classes()
keypairs = {}
for param in params:
name = param['name']
class_type = class_dict[name]
value = class_type.get_search_value(param)
if name == primary_column_name:
name = '_id'
if value:
keypairs.update({name: value})
items = accounts_collection.find(keypairs)
if sort_by:
items = items.sort(sort_by)
with TemporaryFile() as f:
# csv_writer = csv.writer(f)
csv_writer = UnicodeWriter(f)
csv_writer.writerow(all_classes)
for item in items:
csv_columns =[]
primary_key = item['_id']
for name in all_classes:
class_type = class_dict[name]
if name == primary_column_name:
name = '_id'
if name in item:
csv_string = class_type.get_csv_string(item[name])
else:
csv_string = default_csv_string
csv_columns.append(csv_string)
csv_writer.writerow(csv_columns)
f.seek(0)
lines = f.read()
return lines
def main():
reader = UnicodeReader(sys.stdin)
writer = UnicodeWriter(sys.stdout)
writer.writerow([
"gemeente", "stembureau", "postcode", "stemmen", "postcode_google",
"lat", "lng"
])
for row in reader:
result = find_voting_place(row)
writer.writerow(result)
sleep(1)
return 0
class OpmlToCsvConverter(OpmlConverter):
"""Convert OPML file to Todoist CSV."""
EXT = 'csv'
def __init__(self, args):
super(OpmlToCsvConverter, self).__init__(args)
def convert(self):
document_body = self._prepare_document()
with codecs.open(self.target_name, 'w+') as target:
self.writer = UnicodeWriter(target, FIELDNAMES)
self._write_header_row()
for outline in document_body:
self.process_element(outline)
def _prepare_document(self):
tree = ET.parse(self.source_name)
opml = tree.getroot()
return opml.find('body')
def _write_header_row(self):
self.writer.writerow(FIELDNAMES)
def _make_row(self, type='', content='', indent=''):
return [type, content, '', indent, '', '', '', '', '']
def process_element(self, outline, level=1):
# content
row = self._make_row(self.TYPE_TASK, outline.get('text'), str(level))
self.writer.writerow(row)
# note
note = outline.get(self.NOTE_ATTRIB)
if note:
row = self._make_row(self.TYPE_NOTE, note)
self.writer.writerow(row)
# separator
self.writer.writerow(self._make_row())
for subelement in outline.findall('outline'):
self.process_element(subelement, level + 1)
def main():
shapes = get_shapes(sys.argv[1])
writer = UnicodeWriter(sys.stdout)
writer.writerow([
'buurt_code', 'buurt_naam', 'wijk_code', 'gem_code',
'gem_naam'])
for geom, props in shapes:
out_row = []
for fld in [
u'BU_CODE', u'BU_NAAM', u'WK_CODE',
u'GM_CODE', u'GM_NAAM'
]:
out_row.append(props[fld])
writer.writerow(out_row)
return 0
def write_group_by_one_filed(todos, output_path, value_name, values_list):
csv_file = open(output_path, 'wb')
res = group_by_value(todos, value_name, values_list)
print('write: %s' % output_path)
writer = UnicodeWriter(csv_file)
row = ['complete']
row.extend(values_list)
writer.writerow(row)
for row in res:
output_row = [row[0]]
for _, v in row[1].items():
output_row.append(str(v))
writer.writerow(output_row)
def main():
if len(sys.argv) < 6:
print >> sys.stderr, "Usage: merge.py <shape_file> <lat_field> <lon_field> <lat_fallbck> <lon_fallback>"
return 1
reader = UnicodeReader(sys.stdin)
writer = UnicodeWriter(sys.stdout)
header = reader.next()
shapes = get_shapes(sys.argv[1])
out_header = deepcopy(header)
out_header += [
'buurt_code', 'buurt_naam', 'wijk_code', 'wijk_naam', 'gem_code',
'gem_naam'
]
writer.writerow(out_header)
lat_field = sys.argv[2]
lon_field = sys.argv[3]
lat_fb_field = sys.argv[4]
lon_fb_field = sys.argv[5]
for row in reader:
out_row = deepcopy(row)
data = dict(zip(header, row))
if (data[lon_field] != u'-') and (data[lat_field] != u''):
lat = data[lat_field]
lon = data[lon_field]
else:
lat = data[lat_fb_field]
lon = data[lon_fb_field]
if (lat != u'-') and (lon != u'-'):
point = shapely.geometry.Point(float(lat), float(lon))
for shape, props in shapes:
if shape.contains(point):
for fld in [
u'BU_CODE', u'BU_NAAM', u'BU_CODE', u'BU_NAAM',
u'GM_CODE', u'GM_NAAM'
]:
out_row.append(props[fld])
break
if len(out_row) == len(row): # if we did not find anything
out_row += [u'-', u'-', u'-', u'-', u'-', u'-']
writer.writerow(out_row)
return 0
def write_timer(todos, output_path):
csv_file = open(output_path, 'wb')
date_timer = {}
print('write: %s' % output_path)
writer = UnicodeWriter(csv_file)
for todo in todos:
if not isinstance(todo.timer, int):
continue
if todo.completed not in date_timer:
date_timer[todo.completed] = 0
date_timer[todo.completed] += todo.timer
row = ['date', 'timer']
writer.writerow(row)
for date, minutes in date_timer.items():
output_row = [
date.strftime('%Y-%m-%d'), "{0:.2f}".format(minutes / 60.0)
]
writer.writerow(output_row)
def main():
if len(sys.argv) < 3:
print >> sys.stderr, "Usage: merge.py <file1> <file2>"
return 1
places = get_places(sys.argv[2])
election_file = UnicodeReader(open(sys.argv[1]))
headers = election_file.next()
writer = UnicodeWriter(sys.stdout)
writer.writerow([
"gemeente", "stembureau", "postcode", "stemmen", "postcode_google",
"lat", "lng", "stembureau2017", "lat2017", "lon2017"
])
for row in election_file:
result = dict(zip(headers, row))
place = None
if result[u'postcode'] != u'-':
place = find_place_by_postcode(
places, re.sub(r'\s+', u'', result[u'postcode']))
elif result[u'postcode_google'] != u'':
place = find_place_by_postcode(
places, re.sub(r'\s+', u'', result[u'postcode']))
if place is None:
place = find_place_by_muni_and_name(places, result[u'gemeente'],
result[u'stembureau'])
result_row = deepcopy(row)
if place is not None:
result_row.append(place[u'stembureau'])
result_row.append(place[u'Longitude'])
result_row.append(place[u'Latitude'])
else:
result_row.append(u'-')
result_row.append(u'-')
result_row.append(u'-')
# if result_row[-1] != u'-':
# pprint(result_row)
writer.writerow(result_row)
return 0
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import NoSuchElementException
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.proxy import *
file_player_link2 = open("clean_result_player_link2")
result_player_link = pickle.load(file_player_link2)
links = list()
for i in range(len(result_player_link)):
links.append(result_player_link[i][1])
result = list()
result_file = open("result_file.csv", "a")
wr = UnicodeWriter(result_file)
for link in links[6234:]:
proxy = ["173.9.233.186", "54.227.39.120", "194.141.96.1", "218.108.232.190", "80.193.214.233", "125.39.171.194"]
port = [3128, 80, 8080, 843, 3128, 86]
while True:
chosen = random.randint(0, len(proxy)-1)
profile = webdriver.FirefoxProfile()
profile.set_preference("network.proxy.type", 1)
profile.set_preference("network.proxy.http", proxy[chosen])
profile.set_preference("network.proxy.http_port", port[chosen])
profile.update_preferences()
ff = webdriver.Firefox(firefox_profile=profile)
ff.set_page_load_timeout(20)
try:
viaf_code = line[1]
sbn_code = line[2]
except:
pass
if page:
wikipedia[page] = {'viaf': viaf_code,
'sbn': sbn_code}
if viaf_code:
viaf2wiki[viaf_code] = page
if sbn_code:
sbn2wiki[sbn_code] = page
outwikifile = open(OUTWIKIFILE, 'a+')
wikiwriter = UnicodeWriter(outwikifile)
wikipages_to_get = set(wikipages_with_authority_control) - set(wikipedia.keys())
logger.debug('Wikipages with authority control: {no}'.format(
no=len(set(wikipages_with_authority_control))))
logger.debug('no. of keys already collected: {no}'.format(
no=len(set(wikipedia.keys()))))
logger.debug('no. of pages in it.wiki with authority control, still to get: {no}'.format(
no=len(wikipages_to_get)))
count = 0
for page in wikipages_to_get:
count += 1
logger.debug(count)
from unicode_csv import UTF8Recoder, UnicodeReader, UnicodeWriter
rdr = UnicodeReader(open(sys.argv[1]))
tag_re = re.compile('\W', re.UNICODE)
flickr_tags = set()
tag_source = os.path.join(os.path.dirname(__file__), '../data/tags_from_flickr.csv')
with open(tag_source) as f:
tagreader = UnicodeReader(f)
for tagrow in tagreader:
text, raw, author = tagrow[:]
flickr_tags.add(text)
outfile = open('updated_tags.orig.csv', 'w+')
wrtr = UnicodeWriter(outfile)
head = [ 'Normalized', 'Raw', 'Model', 'field' ]
wrtr.writerow(head)
for row in rdr:
new_row = []
ugly, raw, mitch, laura, model, field, basis = row[:]
u = 'MISSING'
if ugly:
u = ugly if ugly in flickr_tags else ('CURR:NO_MATCH:%s' % ugly)
else:
ugly = unicodedata.normalize('NFC', raw)
ugly = tag_re.sub('', ugly.strip().lower())
u = ugly if ugly in flickr_tags else ('NEW:NO_MATCH:%s' % ugly)
new_row = row[:]
import json
import os.path
import sys
import io
from unicode_csv import UnicodeWriter
def get_value_from_dict_or_return_NA(dict, key):
if key in dict and dict[key] != None:
return dict[key]
return "NA"
with io.open('acl_instagram.csv', 'ab') as csv_data:
writer = UnicodeWriter(csv_data, delimiter='`')
with open('acl_instagram.txt') as instagram_file:
for insta_data in instagram_file:
post = json.loads(insta_data)
writer.writerow([
get_value_from_dict_or_return_NA(post, 'user'),
get_value_from_dict_or_return_NA(post, 'post_time'),
get_value_from_dict_or_return_NA(post, 'post_location'),
get_value_from_dict_or_return_NA(post, 'likes_count'),
get_value_from_dict_or_return_NA(post, 'views_count'),
json.dumps(get_value_from_dict_or_return_NA(post, 'comments'))
])
def __init__(self, dest, predicate=None, use_unicode=False):
if use_unicode:
self._writer = UnicodeWriter(dest, delimiter=DELIMITER)
else:
self._writer = csv.writer(dest, delimiter=DELIMITER)
self._predicate = predicate
