1
다음은 코드 작성 전의 원시 데이터입니다.Parsed Json 텍스트에서 한 단어 만 인쇄하십시오.
: 여기import csv
import json
import oauth2 as oauth
import urllib
import sys
import requests
import time
CONSUMER_KEY = ""
CONSUMER_SECRET = ""
ACCESS_KEY = ""
ACCESS_SECRET = ""
class TwitterSearch:
def __init__(self,
ckey = CONSUMER_KEY,
csecret = CONSUMER_SECRET,
akey = ACCESS_KEY,
asecret = ACCESS_SECRET,
query = 'https://api.twitter.com/1.1/search/tweets.{mode}?{query}'
):
consumer = oauth.Consumer(key=ckey, secret=csecret)
access_token = oauth.Token(key=akey, secret=asecret)
self.client = oauth.Client(consumer, access_token)
self.query = query
def search(self, q, mode='json', **queryargs):
queryargs['q'] = q
query = urllib.urlencode(queryargs)
return self.client.request(self.query.format(query=query, mode=mode))
def write_csv(fname, rows, header=None, append=False, **kwargs):
filemode = 'ab' if append else 'wb'
with open(fname, filemode) as outf:
out_csv = csv.writer(outf, **kwargs)
if header:
out_csv.writerow(header)
out_csv.writerows(rows)
def main():
ts = TwitterSearch()
response, data = ts.search('@gmail.com', result_type='recent')
js = json.loads(data)
search_terms = ['@gmail.com']
matches = []
for term in search_terms:
match = [word for word in js if term in word]
matches.append(match)
messages = ([msg['created_at'], msg['text'], msg['user']['id'], matches[0]] for msg in js.get('statuses', []))
write_csv('twitter_gmail.csv', messages, append=True)
if __name__ == '__main__':
main()
{"metadata":{"result_type":"recent","iso_language_code":"et"}
"created_at":"Tue Dec 03 01:41:53 +0000 2013","id":407686093790662656,"id_str":"407686093790662656","text":"@emblems123 [email protected]","source":"\u003ca href=\"http:\/\/twitter.com\/download\/iphone\" rel=\"nofollow\"\u003eTwitter for iPhone\u003c\/a\u003e","truncated":false,"in_reply_to_status_id":407677310821613569,"in_reply_to_status_id_str":"407677310821613569","in_reply_to_user_id":2201997043,"in_reply_to_user_id_str":"2201997043","in_reply_to_screen_name":"emblems123","user":{"id":1220098345,"id_str":"1220098345","name":"PYD","screen_name":"bieberfan12599","location":
Fri Dec 13 03:49:06 +0000 2013,I need some HARD TRAP beats producers help me out [email protected],490060971,[]
제 문제는 구문 분석 된 JS 텍스트의 전자 메일 주소 만 인쇄하려고합니다. 나는 split()을 시도했지만 표현으로 그 것을 할 수 없다. 내가하는 일과 상관없는 것처럼 보입니다. "[]"
"텍스트"의 일부분을 전자 메일로 출력하는 방법을 알고 싶습니다.
import re
string = "Fri Dec 13 03:49:06 +0000 2013,I need some HARD TRAP beats producers help me out [email protected],490060971,[]"
regex = "\[email protected]\w+\.com"
match = re.findall(regex,string)
print match
이 경우 하나의의 모든 경기, 을 포함하는 출력 :
['[email protected]']
그리고