I'm trying with no luck to save the output of an API response into a CSV file in a clear and ordered way, this is the script to retrieve API data:
import json
import requests
import csv
# List of keywords to be checked
keywords = open("/test.txt", encoding="ISO-8859-1")
keywords_to_check = []
try:
for keyword in keywords:
keyword = keyword.replace("\n", "")
keywords_to_check.append(keyword)
except Exception:
print("An error occurred. I will try again!")
pass
apikey = # my api key
apiurl = # api url
apiparams = {
'apikey': apikey,
'keyword': json.dumps(keywords_to_check),
'metrics_location': '2840',
'metrics_language': 'en',
'metrics_network': 'googlesearchnetwork',
'metrics_currency': 'USD',
'output': 'csv'
}
response = requests.post(apiurl, data=apiparams)
jsonize = json.dumps(response.json(), indent=4, sort_keys=True)
if response.status_code == 200:
print(json.dumps(response.json(), indent=4, sort_keys=True))
The output I get is the following:
{
"results": {
"bin": {
"cmp": 0.795286539,
"cpc": 3.645033,
"m1": 110000,
"m10": 90500,
"m10_month": 2,
"m10_year": 2019,
"m11": 135000,
"m11_month": 1,
"m11_year": 2019,
"m12": 135000,
"m12_month": 12,
"m12_year": 2018,
"m1_month": 11,
"m1_year": 2019,
"m2": 110000,
"m2_month": 10,
"m2_year": 2019,
"m3": 110000,
"m3_month": 9,
"m3_year": 2019,
"m4": 135000,
"m4_month": 8,
"m4_year": 2019,
"m5": 135000,
"m5_month": 7,
"m5_year": 2019,
"m6": 110000,
"m6_month": 6,
"m6_year": 2019,
"m7": 110000,
"m7_month": 5,
"m7_year": 2019,
"m8": 90500,
"m8_month": 4,
"m8_year": 2019,
"m9": 90500,
"m9_month": 3,
"m9_year": 2019,
"string": "bin",
"volume": 110000
},
"chair": {
"cmp": 1,
"cpc": 1.751945,
"m1": 1000000,
"m10": 823000,
"m10_month": 2,
"m10_year": 2019,
"m11": 1500000,
"m11_month": 1,
"m11_year": 2019,
"m12": 1500000,
"m12_month": 12,
"m12_year": 2018,
"m1_month": 11,
"m1_year": 2019,
"m2": 1000000,
"m2_month": 10,
"m2_year": 2019,
"m3": 1000000,
"m3_month": 9,
"m3_year": 2019,
"m4": 1220000,
"m4_month": 8,
"m4_year": 2019,
"m5": 1220000,
"m5_month": 7,
"m5_year": 2019,
"m6": 1000000,
"m6_month": 6,
"m6_year": 2019,
"m7": 1000000,
"m7_month": 5,
"m7_year": 2019,
"m8": 1000000,
"m8_month": 4,
"m8_year": 2019,
"m9": 1000000,
"m9_month": 3,
"m9_year": 2019,
"string": "chair",
"volume": 1220000
}, ....
What I'd like to achieve is a csv file showing the following info and ordering, with the columns being string, cmp, cpc and volume:
string;cmp;cpc;volume
bin;0.795286539;3.645033;110000
chair;1;1.751945;1220000
Following Sidous' suggestion I've come to the following:
import pandas as pd
data = response.json()
df = pd.DataFrame.from_dict(data)
df.head()
Which game me the following output:
results
bin {'string': 'bin', 'volume': 110000, 'm1': 1100...
chair {'string': 'chair', 'volume': 1220000, 'm1': 1...
flower {'string': 'flower', 'volume': 1830000, 'm1': ...
table {'string': 'table', 'volume': 673000, 'm1': 82...
water {'string': 'water', 'volume': 673000, 'm1': 67...
Close, but still how can I show "string", "volume" etc as columns and avoid displaying the {'s of the dictioary?
Thanks a lot to whoever can help me sort this out :)
Askew
I propose to save the response in pandas data frame, then store it by pandas (you know csv file are easily handled by pandas).
import pandas as pd
# receiving results in a dictionary
dic = response.json()
# remove the results key from the dictionary
dic = dic.pop("results", None)
# convert dictionary to dataframe
data = pd.DataFrame.from_dict(dic, orient='index')
# string;cmp;cpc;volume
new_data = pd.concat([data['string'], data['cmp'], data['cpc'], data['volume']], axis=1)
# removing the default index (bin and chair keys)
new_data.reset_index(drop=True, inplace=True)
print(new_data)
# saving new_data into a csv file
new_data.to_csv('name_of_file.csv')
You find the csv file in the same directory of the python file (otherwise you can specify it in the .to_csv() method).
You can see the final result in screen shot below.
Open a text file using with open
command and further write the data down by iterating through the whole dict
with open("text.csv", "w+") as f:
f.write('string;cmp;cpc;volume\n')
for res in response.values(): #This is after I assumed that `response` is of type dict
for r in res.values():
f.write(r['string']+';'+str(r['cmp'])+';'+str(r['cpc'])+';'+str(r['volume'])+'\n')
try this:
import pandas as pd
data = response.json()
cleaned_data = []
for key, val in data["results"].items():
cleaned_data.append(val)
df = pd.DataFrame.from_dict(cleaned_data)
df1 = df[["string","cmp","cpc","volume"]]
df1.head()
df1.to_csv("output.csv")
What about using a csv.DictWriter , since your data are almost what it needs to function?
import csv
if __name__ is "__main__":
results = {"chair": {"cmp": 1, "cpc": 3.64}, "bin": {"cmp": 0.5, "cpc": 1.75}} # two rows will do for the example
# Now let's get the data structure we really want: a list of rows
rows = []
for key, value in results:
rows.append(results)
# And, while we're at it, set the string part
rows[-1]["string"] = key
# Create the header
fieldnames = set()
for row in rows:
for fname in row:
fieldnames.add(fname)
# Write to the file
with open("mycsv.csv", "w", newline="") as file_:
writer = csv.DictWriter(file_, fieldnames=fieldnames)
writer.writeheader()
for row in rows:
writer.writerow(row)
You should be good with that kind of stuff, without using any other lib
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.