-
Notifications
You must be signed in to change notification settings - Fork 52
/
Copy pathmain.py
90 lines (72 loc) · 3.05 KB
/
main.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
#!/usr/bin/python
# Usage example:
# python comments.py --videoid='<video_id>'
import httplib2
import os
import sys
import nltk
import csv
from nltk.sentiment.vader import SentimentIntensityAnalyzer
from apiclient.discovery import build_from_document
from apiclient.errors import HttpError
from oauth2client.client import flow_from_clientsecrets
from oauth2client.file import Storage
from oauth2client.tools import argparser, run_flow
CLIENT_SECRETS_FILE = "client_secrets.json"
YOUTUBE_READ_WRITE_SSL_SCOPE = "https://www.googleapis.com/auth/youtube.force-ssl"
YOUTUBE_API_SERVICE_NAME = "youtube"
YOUTUBE_API_VERSION = "v3"
MISSING_CLIENT_SECRETS_MESSAGE = """
WARNING: Please configure OAuth 2.0
To make this sample run you will need to populate the client_secrets.json file
found at:
%s
with information from the APIs Console
https://console.developers.google.com
For more information about the client_secrets.json file format, please visit:
https://developers.google.com/api-client-library/python/guide/aaa_client_secrets
""" % os.path.abspath(os.path.join(os.path.dirname(__file__),
CLIENT_SECRETS_FILE))
def get_authenticated_service(args):
flow = flow_from_clientsecrets(CLIENT_SECRETS_FILE, scope=YOUTUBE_READ_WRITE_SSL_SCOPE,
message=MISSING_CLIENT_SECRETS_MESSAGE)
storage = Storage("%s-oauth2.json" % sys.argv[0])
credentials = storage.get()
if credentials is None or credentials.invalid:
credentials = run_flow(flow, storage, args)
with open("youtube-v3-discoverydocument.json", "r") as f:
doc = f.read()
return build_from_document(doc, http=credentials.authorize(httplib2.Http()))
def get_comment_threads(youtube, video_id, comments=[], token=""):
results = youtube.commentThreads().list(
part="snippet",
pageToken=token,
videoId=video_id,
textFormat="plainText"
).execute()
for item in results["items"]:
comment = item["snippet"]["topLevelComment"]
text = comment["snippet"]["textDisplay"]
comments.append(text)
if "nextPageToken" in results:
return get_comment_threads(youtube, video_id, comments, results["nextPageToken"])
else:
return comments
if __name__ == "__main__":
argparser.add_argument("--videoid",
help="Required; ID for video for which the comment will be inserted.")
args = argparser.parse_args()
if not args.videoid:
exit("Please specify videoid using the --videoid= parameter.")
youtube = get_authenticated_service(args)
try:
video_comment_threads = get_comment_threads(youtube, args.videoid)
sia = SentimentIntensityAnalyzer()
with open('compounds.csv', 'w') as csvfile:
writer = csv.writer(csvfile)
for comment in video_comment_threads:
score = sia.polarity_scores(comment)
writer.writerow([comment, score["compound"]])
print("Logged sentiments of {0} comments to compounds.csv".format(len(video_comment_threads)))
except HttpError as e:
print("An HTTP error %d occurred:\n%s" % (e.resp.status, e.content))