twitterscraper-ruby 0.9.0 → 0.10.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/Gemfile.lock +1 -1
- data/README.md +1 -0
- data/lib/twitterscraper.rb +1 -0
- data/lib/twitterscraper/cli.rb +16 -2
- data/lib/twitterscraper/template.rb +48 -0
- data/lib/version.rb +1 -1
- metadata +2 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: c2429cf6172b5f19caede64ac35f5c796a7c8a67e76fff8dd2f08677fb15406b
|
|
4
|
+
data.tar.gz: 0f32ca6b559a18c4e3aac3205f6503149e372d4d7d1976b1e83db26036d9ff17
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: a36ce6c91a363b64b36deeb3abbaaaebb725f3449f280b70be92532497a94dc5915ba449926acfacfc0d852d52471d258d41140a8891e64b6040bf262d0c347f
|
|
7
|
+
data.tar.gz: a737c7db151190a1493b1a2a92bea304cfcf7512b2ee03fc13c6f25794f5dc727fe548e52cb39eccc2a63261fee0d58fc005920a0e7cd7650d20600e184d79cb
|
data/Gemfile.lock
CHANGED
data/README.md
CHANGED
|
@@ -143,6 +143,7 @@ $ cat tweets.json | jq . | less
|
|
|
143
143
|
| `--limit` | Stop scraping when *at least* the number of tweets indicated with --limit is scraped. | 100 |
|
|
144
144
|
| `--threads` | Set the number of threads twitterscraper-ruby should initiate while scraping for your query. | 2 |
|
|
145
145
|
| `--proxy` | Scrape https://twitter.com/search via proxies. | false |
|
|
146
|
+
| `--format` | The format of the output. | json |
|
|
146
147
|
| `--output` | The name of the output file. | tweets.json |
|
|
147
148
|
|
|
148
149
|
|
data/lib/twitterscraper.rb
CHANGED
data/lib/twitterscraper/cli.rb
CHANGED
|
@@ -25,7 +25,19 @@ module Twitterscraper
|
|
|
25
25
|
}
|
|
26
26
|
client = Twitterscraper::Client.new
|
|
27
27
|
tweets = client.query_tweets(options['query'], query_options)
|
|
28
|
-
|
|
28
|
+
export(tweets) unless tweets.empty?
|
|
29
|
+
end
|
|
30
|
+
|
|
31
|
+
def export(tweets)
|
|
32
|
+
write_json = lambda { File.write(options['output'], generate_json(tweets)) }
|
|
33
|
+
|
|
34
|
+
if options['format'] == 'json'
|
|
35
|
+
write_json.call
|
|
36
|
+
elsif options['format'] == 'html'
|
|
37
|
+
File.write('tweets.html', Template.tweets_embedded_html(tweets))
|
|
38
|
+
else
|
|
39
|
+
write_json.call
|
|
40
|
+
end
|
|
29
41
|
end
|
|
30
42
|
|
|
31
43
|
def generate_json(tweets)
|
|
@@ -53,6 +65,7 @@ module Twitterscraper
|
|
|
53
65
|
'limit:',
|
|
54
66
|
'threads:',
|
|
55
67
|
'output:',
|
|
68
|
+
'format:',
|
|
56
69
|
'proxy',
|
|
57
70
|
'pretty',
|
|
58
71
|
'verbose',
|
|
@@ -61,7 +74,8 @@ module Twitterscraper
|
|
|
61
74
|
options['lang'] ||= ''
|
|
62
75
|
options['limit'] = (options['limit'] || 100).to_i
|
|
63
76
|
options['threads'] = (options['threads'] || 2).to_i
|
|
64
|
-
options['
|
|
77
|
+
options['format'] ||= 'json'
|
|
78
|
+
options['output'] ||= "tweets.#{options['format']}"
|
|
65
79
|
|
|
66
80
|
options
|
|
67
81
|
end
|
|
@@ -0,0 +1,48 @@
|
|
|
1
|
+
module Twitterscraper
|
|
2
|
+
module Template
|
|
3
|
+
module_function
|
|
4
|
+
|
|
5
|
+
def tweets_embedded_html(tweets)
|
|
6
|
+
tweets_html = tweets.map { |t| EMBED_TWEET_HTML.sub('__TWEET_URL__', t.tweet_url) }
|
|
7
|
+
EMBED_TWEETS_HTML.sub('__TWEETS__', tweets_html.join)
|
|
8
|
+
end
|
|
9
|
+
|
|
10
|
+
EMBED_TWEET_HTML = <<~'HTML'
|
|
11
|
+
<blockquote class="twitter-tweet">
|
|
12
|
+
<a href="__TWEET_URL__"></a>
|
|
13
|
+
</blockquote>
|
|
14
|
+
HTML
|
|
15
|
+
|
|
16
|
+
EMBED_TWEETS_HTML = <<~'HTML'
|
|
17
|
+
<html>
|
|
18
|
+
<head>
|
|
19
|
+
<style type=text/css>
|
|
20
|
+
.twitter-tweet {
|
|
21
|
+
margin: 30px auto 0 auto !important;
|
|
22
|
+
}
|
|
23
|
+
</style>
|
|
24
|
+
<script>
|
|
25
|
+
window.twttr = (function(d, s, id) {
|
|
26
|
+
var js, fjs = d.getElementsByTagName(s)[0], t = window.twttr || {};
|
|
27
|
+
if (d.getElementById(id)) return t;
|
|
28
|
+
js = d.createElement(s);
|
|
29
|
+
js.id = id;
|
|
30
|
+
js.src = "https://platform.twitter.com/widgets.js";
|
|
31
|
+
fjs.parentNode.insertBefore(js, fjs);
|
|
32
|
+
|
|
33
|
+
t._e = [];
|
|
34
|
+
t.ready = function(f) {
|
|
35
|
+
t._e.push(f);
|
|
36
|
+
};
|
|
37
|
+
|
|
38
|
+
return t;
|
|
39
|
+
}(document, "script", "twitter-wjs"));
|
|
40
|
+
</script>
|
|
41
|
+
</head>
|
|
42
|
+
<body>
|
|
43
|
+
__TWEETS__
|
|
44
|
+
</body>
|
|
45
|
+
</html>
|
|
46
|
+
HTML
|
|
47
|
+
end
|
|
48
|
+
end
|
data/lib/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: twitterscraper-ruby
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.
|
|
4
|
+
version: 0.10.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- ts-3156
|
|
@@ -68,6 +68,7 @@ files:
|
|
|
68
68
|
- lib/twitterscraper/logger.rb
|
|
69
69
|
- lib/twitterscraper/proxy.rb
|
|
70
70
|
- lib/twitterscraper/query.rb
|
|
71
|
+
- lib/twitterscraper/template.rb
|
|
71
72
|
- lib/twitterscraper/tweet.rb
|
|
72
73
|
- lib/version.rb
|
|
73
74
|
- twitterscraper-ruby.gemspec
|