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
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
|
#!/usr/bin/env python3
from urllib.error import HTTPError
from urllib.request import urlopen, Request
import logging
# from requests_oauthlib import OAuth1Session
from datetime import datetime
import sys
import json
bearer = None
def _format_date(dt):
"""convert a datetime into an RFC 822 formatted date
Input date must be in GMT.
Stolen from PyRSS2Gen.
"""
# Looks like:
# Sat, 07 Sep 2002 00:00:01 GMT
# Can't use strftime because that's locale dependent
#
# Isn't there a standard way to do this for Python? The
# rfc822 and email.Utils modules assume a timestamp. The
# following is based on the rfc822 module.
return "%s, %02d %s %04d %02d:%02d:%02d GMT" % (
["Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"][dt.weekday()],
dt.day,
[
"Jan",
"Feb",
"Mar",
"Apr",
"May",
"Jun",
"Jul",
"Aug",
"Sep",
"Oct",
"Nov",
"Dec",
][dt.month - 1],
dt.year,
dt.hour,
dt.minute,
dt.second,
)
def getBearer():
global bearer
if bearer:
return bearer
headers = {
"Authorization": "Basic Zzl1MXI2SFpYTXg0SXU5UGs5VlNvTzFUdzpmeTIyQjN2QVRRNUI2eGthb1BFdFFRUmtuUGQ1WGZBbnBKVG5hc0ZRa3NyUm5qaVNsaw==",
"Content-Type": "application/x-www-form-urlencoded;charset=UTF-8",
}
data = b"grant_type=client_credentials"
url = "https://api.twitter.com/oauth2/token"
res = urlopen(Request(url, headers=headers, data=data, method="POST"))
response = json.loads(res.read().decode("UTF-8"))
bearer = response["access_token"]
return bearer
def unshorten_urls(title, description, urls):
for url in urls:
shorted_url = url["url"]
long_url = url["expanded_url"]
if "images" in url:
img = url["images"][0]["url"]
long_url_html = '<a href="' + long_url + '"><img src="' + img + '"/></a>'
else:
long_url_html = '<a href="' + long_url + '">' + long_url + "</a>"
description = description.replace(shorted_url, long_url_html)
title = title.replace(shorted_url, long_url)
return title, description
def twitter(user):
# 500.000 Tweets per month
# API KEY = g9u1r6HZXMx4Iu9Pk9VSoO1Tw
# API SECRET KEY = fy22B3vATQ5B6xkaoPEtQQRknPd5XfAnpJTnasFQksrRnjiSlk
headers = {"authorization": "Bearer " + getBearer()}
# Recent = last 7 days
url = (
"https://api.twitter.com/2/tweets/search/recent?query=from:"
+ user
+ "&tweet.fields=created_at,author_id,lang,source,public_metrics,entities&expansions=referenced_tweets.id,attachments.media_keys&media.fields=url"
)
try:
res = urlopen(Request(url, headers=headers))
response = json.loads(res.read().decode("UTF-8"))
except Exception as exc:
logging.error('Request to twitter failed.', exc_info=exc)
return None
feed = {
'title': 'Twitter: ' + user,
'url': 'https://twitter.com/' + user,
'description': 'The latest entries of the twitter account of ' + user,
'content': []
}
if not response["meta"]["result_count"]:
return feed
feed['content'] = [parse_tweet(
user,
tweet,
response.get("includes", {}).get("tweets", []),
response.get("includes", {}).get("media", []),
) for tweet in response["data"]]
return feed
def parse_tweet(user, tweet, included_tweets, included_media):
title = description = tweet["text"]
link = "https://twitter.com/" + user + "/status/" + str(tweet["id"])
# Check included re-tweets / replace by Retweet
for rt in tweet.get("referenced_tweets", []):
if rt["type"] == "retweeted":
rt_info = title[: title.index(":") + 2]
ref_tweet = next(
t for t in included_tweets if t["id"] == rt["id"]
)
title = rt_info + ref_tweet["text"]
description = rt_info + ref_tweet["text"]
title, description = unshorten_urls(
title, description, ref_tweet.get("entities", {}).get("urls", [])
)
elif rt["type"] == "replied_to":
description += "<br/>This was a reply to:<br/>" + rt["id"]
elif rt["type"] == "quoted":
description += '<br/>Quoted tweet:<br/>' + rt["text"]
else:
description += f"<br/><br/>Unknown reference type: {rt['type']}"
title, description = unshorten_urls(
title, description, tweet.get("entities", {}).get("urls", [])
)
# Attach media
enclosures = []
included_media_keys = tweet.get('attachments', {}).get('media_keys', [])
for included_media_key in included_media_keys:
ref_media = next(
t for t in included_media if t["media_key"] == included_media_key
)
if 'url' not in ref_media: continue
if ref_media.get('type', '') == 'photo':
description += "<br/><img src=\"" + ref_media['url'] + "\" />"
else:
enclosures.append(ref_media['url'])
# Append Retweets etc
description += "<br/><br/>"
description += str(tweet["public_metrics"]["retweet_count"]) + " Retweets, "
description += str(tweet["public_metrics"]["like_count"]) + " Likes, "
description += str(tweet["public_metrics"]["reply_count"]) + " Replies, "
description += str(tweet["public_metrics"]["quote_count"]) + " Quotes"
description += "<br/>"
description += "Source: " + tweet["source"]
date = datetime.strptime(tweet["created_at"], "%Y-%m-%dT%H:%M:%S.%fZ")
return {
"title": title,
"url": link,
"content": description,
"date": date,
"enclosures": enclosures,
}
def main(channel):
print(twitter(channel))
if __name__ == "__main__":
if len(sys.argv) != 2:
print("Usage:", sys.argv[0], "<twitter channel>")
sys.exit(1)
main(sys.argv[1])
# twitter('rheinbahn_intim')
# twitter('realDonaldTrump')
|
