We Keep Coding

supplementary quotes appearing in my csv using python code

I did a code to generate multiple addresses and export it in csv
import csv
import ipaddress
import random
from random import shuffle
LAN = ipaddress.ip_network('192.168.0.0/16')
WAN1 = ipaddress.ip_network('11.10.8.0/22')
WAN2 = ipaddress.ip_network('12.10.8.0/22')
LAN_IP_Adresses = [ IP_LAN for IP_LAN in LAN.hosts()]
WAN1_IP_Adresses = [ IP_WAN1 for IP_WAN1 in WAN1.hosts()]
WAN2_IP_Adresses = [ IP_WAN2 for IP_WAN2 in WAN2.hosts()]
index_IP_GW = len(WAN1_IP_Adresses)-1
locations_list=['Abidjan','Abu Dhabi','Adana','Adelaide', 'Ahmadabad','Algiers','Amsterdam','Ankara','Anshan','Athens','BANGKOK','BUCHAREST','BUDAPEST','Bagdad','Bandung','Bangalore','Bangkok','Barcelona','Beirut','Belgrade','Bern','Bogota','Brasilia','Brazzaville','Brussels','Bursa','CAIRO','CARACAS','CONAKRY','Canberra','Casablanca','Changchun','Chengdu','Chicago','Copenhagen','Dakar','MINSK','Madrid','Medina','Nairobi','Napoli','Montreal',
'Odessa','Omdurman','Osaka','Ottawa','PYONGYANG','Paris','Pekin', 'Perth','Philadelphia','Phoenix','Pimpri Chinchwad','Porto','Porto Alegre','QUITO','Qingdao','Rabat','Rajkot','Riadh','Rio de Janeiro','Rome','SANTIAGO','Salvador','Samara','San Antonio','San Francisco','Sao Paulo','Sendai','Seongnam','Seoul','Shanghai','Singapore','Sydney','Taiyuan','Tehran','Tijuana','Tokyo','Toronto','Moscou','Moscow','Mumbai (Bombay)','Munich','México','Milan',
'Tripoli','Tunis','Vienna','Warsaw','Wuhan','Xian','Yaounde','Yokohama', 'Zapopan','hong kong','Dallas','Delhi','Doha','Dublin','Durban','Ecatepec','Frankfurt','Fukuoka','Giza','Hamburg','Havana','Helsinki','Houston','Hyderabad','Istanbul','Jaipur','Jakarta','Jeddah','Johannesburg','KIEV','Kaduna','Kano','Kazan','Kuala Lumpur''Kyoto','LUANDA','Lahore','Lanzhou','Le Caire','Leon','Lima','Lisbon','London','Los Angeles','Lyon','MANILA','Melbourne','New York']
#Site_Nmb=1
def initial_Sites_list_generator(filename='SITES_CI.csv', Number_of_Sites=1000):
file_to_output = open(filename,'w',newline='')
csv_writer = csv.writer(file_to_output,delimiter=',')
Site_Nbr=1
index = 0
csv_writer.writerow(["SITE_NAME", "SERIAL_NUMBER",'"LAN_IP_ADDRESS"','"WAN_IP_ADDRESS1"','"WAN_IP_ADDRESS2"','"GATEWAY_IP_ADDRESS1"','"GATEWAY_IP_ADDRESS2"','"ROUTE_REFLECTOR"','"LOCATIONS"','"HARDWAREMODEL"','"LANINT"','"WANINT1"','"WANINT2"','"BW_OUT"','"BW_IN"'])
for i in range(1,Number_of_Sites+1):
shuffle(locations_list)
location = random.choice(locations_list)
csv_writer.writerow(['"SITE'+ str(Site_Nbr)+'"',"2e70129bde9c4426b9213d4408c300",f'"{(LAN_IP_Adresses[index])}"',f'"{str(WAN1_IP_Adresses[index])}"',f'"{str(WAN2_IP_Adresses[index])}"',f'"{str(WAN1_IP_Adresses[index_IP_GW])}"',f'"{str(WAN2_IP_Adresses[index_IP_GW])}"','"False"',f'"{location}"','"ONEv600"','"gigabitethernet0/2"','"gigabitethernet0/0"','"gigabitethernet0/1"','"10"','"20"'])
Site_Nbr = Site_Nbr+1
index = index+1
file_to_output.close()
initial_Sites_list_generator('SITES_OVP.csv', 1000)
but i got unnecessary quotes added in my csv

You are adding the extra quotes yourself. In your for loop, change this line:
csv_writer.writerow(['"SITE'+ str(Site_Nbr)+'"',"2e70129bde9c4426b9213d4408c300",f'"{(LAN_IP_Adresses[index])}"',f'"{str(WAN1_IP_Adresses[index])}"',f'"{str(WAN2_IP_Adresses[index])}"',f'"{str(WAN1_IP_Adresses[index_IP_GW])}"',f'"{str(WAN2_IP_Adresses[index_IP_GW])}"','"False"',f'"{location}"','"ONEv600"','"gigabitethernet0/2"','"gigabitethernet0/0"','"gigabitethernet0/1"','"10"','"20"'])
to this:
csv_writer.writerow(['SITE'+ str(Site_Nbr)+"2e70129bde9c4426b9213d4408c300",
f'{(LAN_IP_Adresses[index])}',
f'{str(WAN1_IP_Adresses[index])}',
f'{str(WAN2_IP_Adresses[index])}',
f'{str(WAN1_IP_Adresses[index_IP_GW])}',
f'{str(WAN2_IP_Adresses[index_IP_GW])}',
'False',
f'{location}',
'ONEv600',
'gigabitethernet0/2',
'gigabitethernet0/0',
'gigabitethernet0/1',
'10',
'20'])
The CSV writer already adds quotes to strings as appropriate.

I did
csv_writer = csv.writer(file_to_output,delimiter=",",quoting=csv.QUOTE_ALL)
and it worked !

encoding Lithuanian character in xml using python

I have a code:
def convert_df_to_xml(df,fd,ld):
# sukuriam pagrindini elementa (root) su pavadinimu Invoices.
root = ET.Element("Invoices")
root.set("from", str(fd))
root.set("till", str(ld))
for i in range(len(df['partner_id'])):
# pridedam sub elementa.
invoices = ET.SubElement(root, "Invoice")
invoices.set('clientid',df['company_registry'][i])
invoices.set('imones_pavadinimas', df['partner_id'][i])
# pridedam sub-sub elementa.
quebec = ET.SubElement(invoices, "Product")
# susikraunam eiluciu info is dataframe
sectin_1 = ET.SubElement(quebec, "Name")
sectin_1.text = str(df["Name"][i])
sectin_2 = ET.SubElement(quebec, 'Quantity')
sectin_2.text = str(df["time_dif"][i])
sectin_3 = ET.SubElement(quebec, 'Price')
sectin_3.text = str(df["price_unit"][i])
xmlstr = minidom.parseString(ET.tostring(root)).toprettyxml(indent=" ", encoding="UTF-8").decode("UTF-8")
with open("bandomasis_itp_xml_failas_V_1.1.xml", "w") as f:
f.write(xmlstr)
I'm creating xml file from python DataFrame. The problem is that in xml file I got "?" marks instead "ė" character.
In dataframe i have strings with characters "ė,ą,š,ų" and I need them to be in xml file.
My dataframe:
df1 = pd.DataFrame({'partner_id': ['MED GRUPĖ, UAB'], 'Name':['Pirmas'], 'company_registry': ['3432543'],
'time_dif':['2'],'price_unit':['23']})
what is the problem with encoding here?

Transform Nested XML

I am currently looking to parse out a nested XML into a pandas Datatable so I can generate a CSV with each column being an element name and the value of that being the element text but I am having some issues parsing the information out. Below is an example of the nested XML and what I have tried.
The below XML can be quite large with hundreds of different records. This is what I tried:
##Import modules
import xml.etree.ElementTree as ET
import pandas as pd
from lxml import etree
tree = ET.parse("File.xml")
root = tree.getroot()
for subelement in root:
for subsub in subelement:
print(subsub.tag,",", subsub.text, subsub.attrib, subsub.items())
for subelement in root:
for subsub in subelement:
for subsubsub in subsub:
print(subsubsub.tag,",", subsubsub.text, subsubsub.attrib)
<?xml version="1.0" encoding="utf-16"?>
<test1 xmlns="test.xsd">
<test2 ID="123123123" test3="123123">
<test3>Separate</test3>
<test4>AA</test4>
<Comments>BB</Comments>
<test5>
<test6 ID="123123">
<test3>today</test3>
<test7>123 street</test7>
</test6>
</test5>
<test8>
<test10 ID="434234">
<test3>type of work</test3>
<test9>test work</test9>
</test10>
</test8>
<test11>
<test12 ID="234234234">
<test3>Social</test3>
<test14>test</test14>
</test12>
<test12 ID="123123">
<test3>Something Here</test3>
<test13>Some date</test13>
<test14>123123124433</test14>
</test12>
</test11>
<test15>
<test16 ID="6456456456">
<test3>Something Something</test3>
<test14>746745636</test14>
</test16>
</test15>
</test2>
<test2 ID="353453245" test3="list of something">
<test3>Somewhere</test3>
<test4>Someone</test4>
<Comments>Some comment</Comments>
<test5>
<test6 ID="567456756">
<test3>Not today</test3>
<test7>5634643643</test7>
<test17>Some Info</test17>
<test19>Somewhere</test19>
<test18>63243333</test18>
</test6>
</test5>
<test11>
<test12 ID="456436346">
<test3>Pattern</test3>
<test14>436346346</test14>
</test12>
<test12 ID="4364356">
<test3> ID</test3>
<test14>5674567457</test14>
</test12>
<test12 ID="123123123443">
<test3>Other ID</test3>
<test13>54234532452345</test13>
<test14>231423532452345</test14>
</test12>
</test11>
<test15>
<test16 ID="34252345">
<test3>None test</test3>
<test14>456436436346</test14>
</test16>
</test15>
</test2>
</test1>
Update So would the full code look something like this?
###TEST USING EXAMPLE HOTLIST
with open("file.csv", "w", newline='') as fout:
header = ['test3','test4','test7','test9','test13','test14','test17','test18','test19','Comments']
csvout = csv.DictWriter(fout, fieldnames=header)
csvout.writeheader()
row = {}
for _, elem in ET.iterparse('file.xml'):
# strip the namespace from the element tag name; e.g. {Test.xsd}test14 > test14
tag = re.sub("^{.*?}", "", elem.tag)
if tag == 'test2':
if len(row) != 0:
print(row)
csvout.writerow(row)
row = {}
if len(elem) == 0:
text = elem.text
old = row.get(tag)
if old is None:
# first occurrence of the tag
row[tag] = text
elif isinstance(old, str):
# second occurrence of the tag
row[tag] = [old, text]
else:
# already a list
old.append(text)

For nested XML you can use iterparse() function to iterate over all elements in the XML. You would then need to have logic to handle the elements depending on what tag it's looking at to add to a dictionary object to export as a row.
for _, elem in ET.iterparse('file.xml'):
if len(elem) == 0:
print(f'{elem.tag} {elem.attrib} text={elem.text}')
else:
print(f'{elem.tag} {elem.attrib}')
To create a row in a CSV file from the element text then can do something like this. If, for example, the "test2" marks the beginning of a new record then that can be used to write the record to a new row and clear the dictionary for the next record.
If want to output all or some attributes then need to add a few lines of code for that. If attribute names have the same name as element name or multiple elements have same attribute (e.g. ID) then need to address that in your code.
import xml.etree.ElementTree as ET
import re
import csv
with open("out.csv", "w", newline='') as fout:
header = ['test3','test4','test7','test9','test13','test14','test17','test18','test19','Comments']
csvout = csv.DictWriter(fout, fieldnames=header)
csvout.writeheader()
row = {}
for _, elem in ET.iterparse('test.xml'):
# strip the namespace from the element tag name; e.g. {Test.xsd}test14 > test14
tag = re.sub("^{.*?}", "", elem.tag)
if tag == 'test2':
if len(row) != 0:
print(row)
csvout.writerow(row)
row = {}
if len(elem) == 0:
row[tag] = elem.text
Output:
{'test3': 'Something Something', 'test4': 'AA', 'Comments': 'BB', 'test7': '123 street', 'test9': 'test work', 'test14': '746745636', 'test13': 'Some date'}
{'test3': 'None test', 'test4': 'Someone', 'Comments': 'Some comment', 'test7': '5634643643', 'test17': 'Some Info', 'test19': 'Somewhere', 'test18': '63243333', 'test14': '456436436346', 'test13': '54234532452345'}
CSV Output:
test3,test4,test7,test9,test13,test14,test17,test18,test19,Comments
Something Something,AA,123 street,test work,Some date,746745636,,,,BB
None test,Someone,5634643643,,54234532452345,456436436346,Some Info,63243333,Somewhere,Some comment
Update:
If want to handle duplicate tags and create a list of values then try something like this:
if len(elem) == 0:
text = elem.text
old = row.get(tag)
if old is None:
# first occurrence
row[tag] = text
elif isinstance(old, str):
# second occurrence > create list
row[tag] = [old, text]
else:
old.append(text)

Python - How to count specific section in a list

I'm brand new to python and I'm struggling how to add certain sections of a cvs file in python. I'm not allowed to use "import cvs"
I'm importing the TipJoke CVS file from https://vincentarelbundock.github.io/Rdatasets/datasets.html
This is the only code I have so far that worked and I'm at a total loss on where to go from here.
if __name__ == '__main__':
from pprint import pprint
from string import punctuation
f = open("TipJoke.csv", "r")
tipList = []
for line in f:
#deletes the quotes
line = line.replace('"', '')
tipList.append(line)
pprint(tipList[])
Output:
[',Card,Tip,Ad,Joke,None\n',
'1,None,1,0,0,1\n',
'2,Joke,1,0,1,0\n',
'3,Ad,0,1,0,0\n',
'4,None,0,0,0,1\n',
'5,None,1,0,0,1\n',
'6,None,0,0,0,1\n',
'7,Ad,0,1,0,0\n',
'8,Ad,0,1,0,0\n',
'9,None,0,0,0,1\n',
'10,None,0,0,0,1\n',
'11,None,1,0,0,1\n',
'12,Ad,0,1,0,0\n',
'13,None,0,0,0,1\n',
'14,Ad,1,1,0,0\n',
'15,Joke,1,0,1,0\n',
'16,Joke,0,0,1,0\n',
'17,Joke,1,0,1,0\n',
'18,None,0,0,0,1\n',
'19,Joke,0,0,1,0\n',
'20,None,0,0,0,1\n',
'21,Ad,1,1,0,0\n',
'22,Ad,1,1,0,0\n',
'23,Ad,0,1,0,0\n',
'24,Joke,0,0,1,0\n',
'25,Joke,1,0,1,0\n',
'26,Joke,0,0,1,0\n',
'27,None,1,0,0,1\n',
'28,Joke,1,0,1,0\n',
'29,Joke,1,0,1,0\n',
'30,None,1,0,0,1\n',
'31,Joke,0,0,1,0\n',
'32,None,1,0,0,1\n',
'33,Joke,1,0,1,0\n',
'34,Ad,0,1,0,0\n',
'35,Joke,0,0,1,0\n',
'36,Ad,1,1,0,0\n',
'37,Joke,0,0,1,0\n',
'38,Ad,0,1,0,0\n',
'39,Joke,0,0,1,0\n',
'40,Joke,0,0,1,0\n',
'41,Joke,1,0,1,0\n',
'42,None,0,0,0,1\n',
'43,None,0,0,0,1\n',
'44,Ad,0,1,0,0\n',
'45,None,0,0,0,1\n',
'46,None,0,0,0,1\n',
'47,Ad,0,1,0,0\n',
'48,Joke,0,0,1,0\n',
'49,Joke,1,0,1,0\n',
'50,None,1,0,0,1\n',
'51,None,0,0,0,1\n',
'52,Joke,1,0,1,0\n',
'53,Joke,1,0,1,0\n',
'54,Joke,0,0,1,0\n',
'55,None,1,0,0,1\n',
'56,Ad,0,1,0,0\n',
'57,Joke,0,0,1,0\n',
'58,None,0,0,0,1\n',
'59,Ad,0,1,0,0\n',
'60,Joke,1,0,1,0\n',
'61,Ad,0,1,0,0\n',
'62,None,1,0,0,1\n',
'63,Joke,0,0,1,0\n',
'64,Ad,0,1,0,0\n',
'65,Joke,0,0,1,0\n',
'66,Ad,0,1,0,0\n',
'67,Ad,0,1,0,0\n',
'68,Ad,0,1,0,0\n',
'69,None,0,0,0,1\n',
'70,Joke,1,0,1,0\n',
'71,None,1,0,0,1\n',
'72,None,0,0,0,1\n',
'73,None,0,0,0,1\n',
'74,Joke,0,0,1,0\n',
'75,Ad,1,1,0,0\n',
'76,Ad,0,1,0,0\n',
'77,Ad,1,1,0,0\n',
'78,Joke,0,0,1,0\n',
'79,Joke,0,0,1,0\n',
'80,Ad,1,1,0,0\n',
'81,Ad,0,1,0,0\n',
'82,None,0,0,0,1\n',
'83,Ad,0,1,0,0\n',
'84,Joke,0,0,1,0\n',
'85,Joke,0,0,1,0\n',
'86,Ad,1,1,0,0\n',
'87,None,1,0,0,1\n',
'88,Joke,1,0,1,0\n',
'89,Ad,0,1,0,0\n',
'90,None,0,0,0,1\n',
'91,None,0,0,0,1\n',
'92,Joke,0,0,1,0\n',
'93,Joke,0,0,1,0\n',
'94,Ad,0,1,0,0\n',
'95,Ad,0,1,0,0\n',
'96,Ad,0,1,0,0\n',
'97,Joke,1,0,1,0\n',
'98,None,0,0,0,1\n',
'99,None,0,0,0,1\n',
'100,None,1,0,0,1\n',
'101,Joke,0,0,1,0\n',
'102,Joke,0,0,1,0\n',
'103,Ad,1,1,0,0\n',
'104,Ad,0,1,0,0\n',
'105,Ad,0,1,0,0\n',
'106,Ad,1,1,0,0\n',
'107,Ad,0,1,0,0\n',
'108,None,0,0,0,1\n',
'109,Ad,0,1,0,0\n',
'110,Joke,1,0,1,0\n',
'111,None,0,0,0,1\n',
'112,Ad,0,1,0,0\n',
'113,Ad,0,1,0,0\n',
'114,None,0,0,0,1\n',
'115,Ad,0,1,0,0\n',
'116,None,0,0,0,1\n',
'117,None,0,0,0,1\n',
'118,Ad,0,1,0,0\n',
'119,None,1,0,0,1\n',
'120,Ad,1,1,0,0\n',
'121,Ad,0,1,0,0\n',
'122,Ad,1,1,0,0\n',
'123,None,0,0,0,1\n',
'124,None,0,0,0,1\n',
'125,Joke,1,0,1,0\n',
'126,Joke,1,0,1,0\n',
'127,Ad,0,1,0,0\n',
'128,Joke,0,0,1,0\n',
'129,Joke,0,0,1,0\n',
'130,Ad,0,1,0,0\n',
'131,None,0,0,0,1\n',
'132,None,0,0,0,1\n',
'133,None,0,0,0,1\n',
'134,Joke,1,0,1,0\n',
'135,Ad,0,1,0,0\n',
'136,None,0,0,0,1\n',
'137,Joke,0,0,1,0\n',
'138,Ad,0,1,0,0\n',
'139,Ad,0,1,0,0\n',
'140,None,0,0,0,1\n',
'141,Joke,0,0,1,0\n',
'142,None,0,0,0,1\n',
'143,Ad,0,1,0,0\n',
'144,None,1,0,0,1\n',
'145,Joke,0,0,1,0\n',
'146,Ad,0,1,0,0\n',
'147,Ad,0,1,0,0\n',
'148,Ad,0,1,0,0\n',
'149,Joke,1,0,1,0\n',
'150,Ad,1,1,0,0\n',
'151,Joke,1,0,1,0\n',
'152,None,0,0,0,1\n',
'153,Ad,0,1,0,0\n',
'154,None,0,0,0,1\n',
'155,None,0,0,0,1\n',
'156,Ad,0,1,0,0\n',
'157,Ad,0,1,0,0\n',
'158,Joke,0,0,1,0\n',
'159,None,0,0,0,1\n',
'160,Joke,1,0,1,0\n',
'161,None,1,0,0,1\n',
'162,Ad,1,1,0,0\n',
'163,Joke,0,0,1,0\n',
'164,Joke,0,0,1,0\n',
'165,Ad,0,1,0,0\n',
'166,Joke,1,0,1,0\n',
'167,Joke,1,0,1,0\n',
'168,Ad,0,1,0,0\n',
'169,Joke,1,0,1,0\n',
'170,Joke,0,0,1,0\n',
'171,Ad,0,1,0,0\n',
'172,Joke,0,0,1,0\n',
'173,Joke,0,0,1,0\n',
'174,Ad,0,1,0,0\n',
'175,None,0,0,0,1\n',
'176,Joke,1,0,1,0\n',
'177,Ad,0,1,0,0\n',
'178,Joke,0,0,1,0\n',
'179,Joke,0,0,1,0\n',
'180,None,0,0,0,1\n',
'181,None,0,0,0,1\n',
'182,Ad,0,1,0,0\n',
'183,None,0,0,0,1\n',
'184,None,0,0,0,1\n',
'185,None,0,0,0,1\n',
'186,None,0,0,0,1\n',
'187,Ad,0,1,0,0\n',
'188,None,1,0,0,1\n',
'189,Ad,0,1,0,0\n',
'190,Ad,0,1,0,0\n',
'191,Ad,0,1,0,0\n',
'192,Joke,1,0,1,0\n',
'193,Joke,0,0,1,0\n',
'194,Ad,0,1,0,0\n',
'195,None,0,0,0,1\n',
'196,Joke,1,0,1,0\n',
'197,Joke,0,0,1,0\n',
'198,Joke,1,0,1,0\n',
'199,Ad,0,1,0,0\n',
'200,None,0,0,0,1\n',
'201,Joke,1,0,1,0\n',
'202,Joke,0,0,1,0\n',
'203,Joke,0,0,1,0\n',
'204,Ad,0,1,0,0\n',
'205,None,0,0,0,1\n',
'206,Ad,0,1,0,0\n',
'207,Ad,0,1,0,0\n',
'208,Joke,0,0,1,0\n',
'209,Ad,0,1,0,0\n',
'210,Joke,0,0,1,0\n',
'211,None,0,0,0,1\n']
I'm currently trying to find the Total number of entries of the specified card type and the Percentage of tips given for the specified card type with two decimal places of precision. The tip column is the 0 or 1 right after the card type (None, Ad, Joke).

if you are allowed with pandas library then
import pandas as pd
df = pd.read_csv("TipJoke.csv")
df is a pandas dataframe object in which you can perform multiple filtering task according to your need.
for example if you want to get data for Joke you can filter like this:
print(df[df["Card"] == "Joke"])
Though, i'm just providing you the direction , not whole logic for your question.

This works
from pprint import pprint
from string import punctuation
counts = {"Joke": 0, "Ad": 0, "None": 0}
with open("TipJoke.csv", "r") as f:
for line in f:
line_clean = line.replace('"', "").replace("\n", "").split(",")
try:
counts[line_clean[1]] += int(line_clean[2])
except:
pass
print(counts)

Python 3: XML Tag Value not being written to csv file

My python 3 script takes an xml file and creates a csv file.
Small excerpt of xml file:
<?xml version="1.0" encoding="UTF-8" ?>
<metadata>
<dc>
<title>Golden days for boys and girls, 1895-03-16, v. XVI #17</title>
<subject>Children's literature--Children's periodicals</subject>
<description>Archives & Special Collections at the Thomas J. Dodd Research Center, University of Connecticut Libraries</description>
<publisher>James Elverson, 1880-</publisher>
<date>1895-06-15</date>
<type>Text | periodicals</type>
<format>image/jp2</format>
<handle>http://hdl.handle.net/11134/20002:860074494</handle>
<accessionNumber/>
<barcode/>
<identifier>20002:860074494 | local: 868010272 | local: 997186613502432 | local: 39153019382870 | hdl:  | http://hdl.handle.net/11134/20002:860074494</identifier>
<rights>These Materials are provided for educational and research purposes only. The University of Connecticut Libraries hold the copyright except where noted. Permission must be obtained in writing from the University of Connecticut Libraries and/or theowner(s) of the copyright to publish reproductions or quotations beyond "fair use." | The collection is open and available for research.</rights>
<creator/>
<relation/>
<coverage/>
<language/>
</dc>
</metadata>
Python3 code:
import csv
import xml.etree.ElementTree as ET
tree = ET.ElementTree(file='ctda_set1_uniqueTags.xml')
doc = ET.parse("ctda_set1_uniqueTags.xml")
root = tree.getroot()
oaidc_data = open('ctda_set1_uniqueTags.csv', 'w', encoding='utf-8')
titles = 'dc/title'
subjects = 'dc/subject'
csvwriter = csv.writer(oaidc_data)
oaidc_head = ['Title', 'Subject', 'Description', 'Publisher', 'Date', 'Type', 'Format', 'Handle', 'Accession Number', 'Barcode', 'Identifiers', 'Rights', 'Creator', 'Relation', 'Coverage', 'Language']
count = 0
for member in root.findall('dc'):
if count == 0:
csvwriter.writerow(oaidc_head)
count = count + 1
dcdata = []
titles = member.find('title').text
dcdata.append(titles)
subjects = member.find('subject').text
dcdata.append(subjects)
descriptions = member.find('description').text
dcdata.append(descriptions)
publishers = member.find('publisher').text
dcdata.append(publishers)
dates = member.find('date').text
dcdata.append(dates)
types = member.find('type').text
dcdata.append(types)
formats = member.find('format').text
dcdata.append(formats)
handle = member.find('handle').text
dcdata.append(handle)
accessionNo = member.find('accessionNumber').text
dcdata.append(accessionNo)
barcodes = member.find('barcode').text
dcdata.append(barcodes)
identifiers = member.find('identifier').text
dcdata.append(identifiers)
rt = member.find('rights').text
print(member.find('rights').text)
dcdata.append('rt')
ct = member.find('creator').text
dcdata.append('ct')
rt = member.find('relation').text
dcdata.append('rt')
ce = member.find('coverage').text
dcdata.append('ce')
lang = member.find('language').text
dcdata.append('lang')
csvwriter.writerow(dcdata)
oaidc_data.close()
Everything works as expected except for rt, ce, and lang. What happens is that in the csv, all the data is written with the comma delimiter. For rt, the value is always rt, for ce, ce, lang, lang, etc.
Here's a snippet of the output:
Title,Subject,Description,Publisher,Date,Type,Format,Handle,Accession Number,Barcode,Identifiers,Rights,Creator,Relation,Coverage,Language
"Golden days for boys and girls, 1895-03-16, v. XVI #17",Children's literature--Children's periodicals,"Archives & Special Collections at the Thomas J. Dodd Research Center, University of Connecticut Libraries","James Elverson, 1880-",1895-06-15,Text | periodicals,image/jp2,hdl.handle.net/11134/20002:860074494,,,20002:860074494 | local: 868010272 | local: 997186613502432 | local: 39153019382870,**rt,ct,rt,ce,lang**
Some of the rights statements get very long - perhaps that's the issue. That's why I added the print(member.find('rights')) to see the output. The text is printed just fine. The text just isn't written to the csv. What I'd like is to have the value or text written for these xml tags. Any help would be appreciated.
Thanks.
Jennifer

In the line dcdata.append('rt') there is no need for the quotes. Try dcdata.append(rt). Similarly, there are unnecessary quotes in the ce and lang lines.