SPJA/Twitter API at master · PicklePinie/SPJA · GitHub

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
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
//this code does not work how it should, but it does something. And if it is somehow working, im not touching it.

import json
import os
import re
from resizeimage import resizeimage
import mechanicalsoup
from datetime import datetime
from PIL import Image
from io import BytesIO
from urllib.parse import urlencode

import requests

def create_client():
    consumer = oauth.Consumer(key=CONSUMER_KEY, secret=CONSUMER_SECRET)
    access_token = oauth.Token(key=ACCESS_KEY, secret=ACCESS_SECRET)
    client = oauth.Client(consumer, access_token)

    return client


# Twitter API documentation: https://developer.twitter.com/en/docs.html
API_URL = 'https://api.twitter.com/1.1/'
CLIENT = create_client()


def send_tweet(status):
    """
    1 point.
    Send a tweet with the given `status`.
    Return the response from client.request call.

    Use the provided `CLIENT` variable. Don't forget to urlencode the
    URL parameters.

    Example:
        res = send_tweet('Hello!')
        assert int(res['status']) == 2OO
    """
    '''
    f = {'status':status}
    res, data = CLIENT.request("https://api.twitter.com/1.1/statuses/update.json?"+urlencode(f), method="POST")
    return res
    '''
    pass


def format_date(origin_date):
    new_date = origin_date[-4:] + '-' + origin_date[4:7] + '-' + origin_date[8:10]
    current = datetime.strptime(new_date, "%Y-%b-%d").strftime('%Y-%m-%d')
    return current


def what_guido_says(since, until, keyword):
    """
    2 points.
    Return a list of tweets originating from the Twitter account 'gvanrossum'
    that were posted between `since` and `until` and contain `keyword`.
    Each entry in the list should be a tuple (tweet_text, is_retweet).
    tweet_text should be the text of the tweet
    is_retweet is a boolean stating whether the tweet is a retweet or not

    Use the provided `CLIENT` variable. Don't forget to urlencode the
    URL parameters.

    Example:
        what_guido_says('2018-10-20', '2018-10-25', 'Python')
        # [('blabla', False), ('RT: blablabla', True)]

   """
    url_parameters = {
        'screen_name': 'gvanrossum',
        'hashtags': [keyword],
    }
    request_url = API_URL + 'statuses/user_timeline.json?' + urlencode(url_parameters)
    res, data = CLIENT.request(request_url, method='GET')
    json_tweets = json.loads(data.decode())
    tupl = []
    for tweet in json_tweets:
        current = format_date(tweet['created_at'])
        text = tweet['text']
        retweeted = tweet['retweeted']
        if (since < current < until):
            tupl.append((text, retweeted))

    return tupl

    # print(current)
    # print(since)


'''
    for tweet in json_tweets:
        # Sat Oct 20 21:36:17 +0000 2018
        current = format_date(['created_at'])
        print(current)
        if (since < current < until):
            tupl += tweet['text']
            tupl += tweet['retweeted']
    print(tupl)
    # print(new_since)
'''

''' print('for tweet in json_tweets: ')
        print('tweet: ')
        print(tweet)
        print('\n\n')
        print('screen_name:')
       # print(tweet['screen_name'])
        print('text:')
        print(tweet['text'])
        print('retweeted:')
        print(tweet['retweeted'])
        print('created_at:')
        print(tweet['created_at'])
      #  for key in tweet:
      #      print(' tweet[key]: ' + key)
      #      print(tweet[key])
        print('\n')
        #print('tweet: ')
        #print(tweet)
        print('konec tweetu--------------------------------------------------------------\n')
   # print(json_tweets['text'])


what_guido_says('2018-10-20', '2018-10-25', 'Python')


'''


def scrape_images(url):
    """
    3 points.
    Download the web page from the given `url` and find all images on the page.
    Then download each image and write it to the filesystem under its filename.

    Regex cheatsheet: https://medium.com/factory-mind/regex-tutorial-a-simple-cheatsheet-by-examples-649dc1c3f285

    Example:
        Web page asd.cz: <html>....<img src="images/ahoj.jpg" />...</html>

        scrape_images('http://asd.cz')
        # creates file 'ahoj.jpg' with the image content ('images/' is ignored)

    Hint:
        Either download the web page and parse the images using regular expressions,
        or use the MechanicalSoup (https://mechanicalsoup.readthedocs.io/en/stable/tutorial.html)
        library to extract images from the page.
    """
    # r = requests.get(url)
    # print(url)
    # <img([\w\W]+?)/>
    # p = re.compile('<img([\w\W]+?)/>')
    # p = re.compile('<img .+?>')
    # matches = re.search('<img.+?>', r.text)
    # matches = re.findall('<img.*src=("[^"]+").*>', r.text)
    # for match in matches:
    #    print(match)
    # print(matches)
    # print(r.text)

    browser = mechanicalsoup.StatefulBrowser()
    browser.open(url)
    matches = browser.get_current_page().find_all('img')
    for match in matches:
        img_url = url + match['src']
        image = browser.open(img_url).content
        image_name = img_url.split('/')[-1]

        with open(image_name, 'wb') as f:
            f.write(image)


'''
def create_collage(width, height, list_of_images):

    browser = mechanicalsoup.StatefulBrowser()
    Picturewidth = width // 5
    Pictureheight = height // 2
    size = Picturewidth, Pictureheight
    new_im = Image.new('RGB', (450, 300))
    for p in list_of_images:
        image = browser.open(p).content
    for col in range(0, width):
        for row in range(0, height):
            #image = Image.eval(p, lambda x: x + (col + row) / 30)
            image.eval(p, lambda x: x + (col + row) / 30)
            new_im.paste(p, (col, row))
            new_im.save("Collage" + ".jpg")
'''


def load_and_collage(width, height, list_of_images):
    #browser = mechanicalsoup.StatefulBrowser()
    cols = 5
    rows = 2
    thumbnail_width = width // cols
    thumbnail_height = height // rows
    size = (thumbnail_width, thumbnail_height)
    new_im = Image.new('RGB', (width, height))
    ims = []
    for p in list_of_images:
        gimme200plz = requests.get(p)
        #im = Image.frombytes("RGB", size, gimme200plz)
        im = Image.open(BytesIO(gimme200plz.content))
        im = im.resize(size)
        ims.append(im)
    i = 0
    x = 0
    y = 0
    #print(type(ims[0]))
    #print(type(ims))
    for col in range(cols):
        for row in range(rows):
            #print(i, x, y)
            new_im.paste(ims[i], (x, y))
            i += 1
            y += thumbnail_height
        x += thumbnail_width
        y = 0

    new_im.save("CollagetestforDusan.jpg")


def bonus_catzz():
    """
    1 point (bonus).
    Download the latest 10 tweets from the Twitter account CatMemes.
    Download all images contained in those tweets and combine them into
    one large image containing the latest cat memes. Write the collage image
    to the filesystem.

    Hint: use the pillow library to merge images together
    """
    # https://api.twitter.com/1.1/statuses/user_timeline.json
    # GET https://api.twitter.com/1.1/statuses/user_timeline.json?screen_name=twitterapi&count=2
    how_much_images = 10

    url_parameters = {
        'screen_name': 'CatMemes',
        'count': how_much_images + 5  # nepodarilo se mi osetrit jestli tam obrazek je nebo ne
    }
    request_url = API_URL + 'statuses/user_timeline.json?' + urlencode(url_parameters)
    res, data = CLIENT.request(request_url, method='GET')
    json_tweets = json.loads(data.decode())
    #i = 0
    #browser = mechanicalsoup.StatefulBrowser()
    img_position = set()
    for tweet in json_tweets:
        ext_ent = tweet['extended_entities']
        media = ext_ent.get('media', [])
        if len(media) > 0 and len(img_position) < how_much_images:
            img_position.add(media[0]['media_url'])

    #print('\n')
    # print(media)
    #print(img_position)
    #print(len(img_position))
    load_and_collage(2000, 1000, img_position)


bonus_catzz()