twittercrawler 0.0.8 → 0.0.9
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/lib/twitter_parser.rb +22 -0
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: bd66392453ee594f240aba2f3e958c171e516adf
|
|
4
|
+
data.tar.gz: 66d6b2afd3da543cf76c1cc0db0e68a3d81d63b7
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 7f55deb6274e2b9cd4f937330883e7c0cc45755205781bc5ac36753893b29ee68bafbb4cf348cb08f0d85cb6c7a8d86168f06083a9e7d19b79379825b5071aa6
|
|
7
|
+
data.tar.gz: 1bb607b0c4442a727f03d350cfce0d37b477598cb731e9fe6170f32dd13ad8e7ed664cdb61f10243044b296b7eb36ba952635a895b83abd9a4fa89f0348ddb1a
|
data/lib/twitter_parser.rb
CHANGED
|
@@ -1,7 +1,9 @@
|
|
|
1
1
|
require 'nokogiri'
|
|
2
2
|
require 'pry'
|
|
3
|
+
require 'twitter-text'
|
|
3
4
|
|
|
4
5
|
class TwitterParser
|
|
6
|
+
include Twitter::Extractor
|
|
5
7
|
def initialize(tweet)
|
|
6
8
|
@tweet = Nokogiri::HTML.parse(tweet)
|
|
7
9
|
end
|
|
@@ -14,6 +16,9 @@ class TwitterParser
|
|
|
14
16
|
username: get_username,
|
|
15
17
|
fullname: get_fullname,
|
|
16
18
|
user_id: get_user_id,
|
|
19
|
+
profile_pic: get_profile_pic,
|
|
20
|
+
hashtags: get_hashtags,
|
|
21
|
+
mentioned_urls: get_mentioned_urls,
|
|
17
22
|
reply_to_user: get_reply_to_user[0],
|
|
18
23
|
reply_to_uid: get_reply_to_user[1],
|
|
19
24
|
tweet_time: get_tweet_time,
|
|
@@ -29,6 +34,23 @@ class TwitterParser
|
|
|
29
34
|
end
|
|
30
35
|
end
|
|
31
36
|
|
|
37
|
+
# Get the link to the profile pic
|
|
38
|
+
def get_profile_pic
|
|
39
|
+
@tweet.css("img.avatar")[0]['src']
|
|
40
|
+
end
|
|
41
|
+
|
|
42
|
+
# Get the URLS in the tweet
|
|
43
|
+
def get_mentioned_urls
|
|
44
|
+
tweet = get_tweet_text
|
|
45
|
+
return extract_urls(tweet)
|
|
46
|
+
end
|
|
47
|
+
|
|
48
|
+
# Get the hashtags in the tweet
|
|
49
|
+
def get_hashtags
|
|
50
|
+
tweet = get_tweet_text
|
|
51
|
+
return extract_hashtags(tweet)
|
|
52
|
+
end
|
|
53
|
+
|
|
32
54
|
# Get the username
|
|
33
55
|
def get_username
|
|
34
56
|
@tweet.css(".username").text
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: twittercrawler
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.9
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- M. C. McGrath
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2017-02-
|
|
11
|
+
date: 2017-02-22 00:00:00.000000000 Z
|
|
12
12
|
dependencies: []
|
|
13
13
|
description: Crawls Twitter
|
|
14
14
|
email: shidash@shidash.com
|