twittercrawler 0.0.5 → 0.0.6
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/twitter_parser.rb +2 -1
- data/lib/twittercrawler.rb +48 -36
- 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: 8b2a8f686154fcb64246ed8c3bef02f324df3892
|
4
|
+
data.tar.gz: f8219382c56cfacad13e7fbd55a25e156280976f
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: f21e73e1bd854174182fee749153be4499c2b2f6742ae6ca09aa1e85e2d100e9eab9e2af3898400aa0f0bb6d9b071292cf4393d80b45cfaf37d0e22780a0834b
|
7
|
+
data.tar.gz: 7a8c376ffcaaeb0ae55964251dd7a0efaf5bece5fd81a03c99eed231784bc29d1f5c02855b31ee06931faa97e3da988146210afecfbb6a0304497fd0684f12f1
|
data/lib/twitter_parser.rb
CHANGED
data/lib/twittercrawler.rb
CHANGED
@@ -2,14 +2,14 @@ require 'requestmanager'
|
|
2
2
|
require 'selenium-webdriver'
|
3
3
|
require 'pry'
|
4
4
|
require 'nokogiri'
|
5
|
+
require 'curb'
|
5
6
|
|
6
7
|
load 'twitter_parser.rb'
|
7
8
|
|
8
9
|
class TwitterCrawler
|
9
|
-
def initialize(search_term, operator,
|
10
|
+
def initialize(search_term, operator, cm_hash)
|
10
11
|
@search_term = search_term
|
11
12
|
@operator = operator
|
12
|
-
@requests = requests
|
13
13
|
@output = Array.new
|
14
14
|
|
15
15
|
# Handle crawler manager info
|
@@ -26,45 +26,56 @@ class TwitterCrawler
|
|
26
26
|
end
|
27
27
|
end
|
28
28
|
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
|
29
|
+
# Parse the tweets into html
|
30
|
+
def parse_tweets(tweets)
|
31
|
+
return tweets.map do |tweet|
|
32
|
+
parser = TwitterParser.new(tweet.to_html)
|
33
|
+
parser.parse_tweet
|
34
|
+
end
|
34
35
|
end
|
35
36
|
|
36
|
-
#
|
37
|
-
def
|
38
|
-
|
39
|
-
|
40
|
-
|
41
|
-
#
|
42
|
-
|
43
|
-
|
44
|
-
tweet_html = tweet.attribute("innerHTML")
|
45
|
-
parser = TwitterParser.new(tweet_html)
|
46
|
-
parsed_tweet = parser.parse_tweet
|
47
|
-
|
48
|
-
# Report results
|
49
|
-
if parsed_tweet
|
50
|
-
report_results([parsed_tweet], parsed_tweet[:tweet_link])
|
51
|
-
end
|
37
|
+
# Generate the query url for Twitter
|
38
|
+
def gen_query_url(start_tweet, end_tweet)
|
39
|
+
# Base query url
|
40
|
+
query_url = "https://twitter.com/i/search/timeline?f=tweets&vertical=news&q="+gen_query+"&src=typd&include_available_features=1&include_entities=1"
|
41
|
+
|
42
|
+
# Gen query URL
|
43
|
+
if start_tweet && end_tweet
|
44
|
+
query_url += "&max_position=TWEET-"+start_tweet+"-"+end_tweet
|
52
45
|
end
|
46
|
+
return query_url
|
53
47
|
end
|
54
48
|
|
55
|
-
#
|
56
|
-
def
|
57
|
-
#
|
58
|
-
|
59
|
-
|
60
|
-
tweets[
|
61
|
-
|
62
|
-
#
|
63
|
-
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
|
49
|
+
# Query tweets
|
50
|
+
def query_tweets(start_tweet, end_tweet)
|
51
|
+
# Run Query and parse results
|
52
|
+
c = Curl::Easy.perform(gen_query_url(start_tweet, end_tweet))
|
53
|
+
curl_items = JSON.parse(c.body_str)
|
54
|
+
tweets = Nokogiri::HTML.parse(curl_items["items_html"]).css(".tweet") if curl_items["items_html"]
|
55
|
+
|
56
|
+
# Save results
|
57
|
+
parsed_tweets = parse_tweets(tweets)
|
58
|
+
report_results(parsed_tweets, "Saving "+parsed_tweets.length.to_s+" tweets")
|
59
|
+
|
60
|
+
# Recurse when needed
|
61
|
+
if !parsed_tweets.empty?
|
62
|
+
start_tweet, end_tweet = get_tweet_range(parsed_tweets, end_tweet)
|
63
|
+
query_tweets(start_tweet, end_tweet)
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
# Get the ID for a tweet
|
68
|
+
def get_tweet_id(tweet)
|
69
|
+
return tweet[:tweet_link].split("/").last
|
70
|
+
end
|
71
|
+
|
72
|
+
# Get start and end tweets
|
73
|
+
def get_tweet_range(parsed_tweets, end_tweet)
|
74
|
+
if end_tweet # Keeep latest tweet as same
|
75
|
+
return get_tweet_id(parsed_tweets.last), end_tweet
|
76
|
+
else # Get updated start tweet
|
77
|
+
return get_tweet_id(parsed_tweets.last), get_tweet_id(parsed_tweets.first)
|
78
|
+
end
|
68
79
|
end
|
69
80
|
|
70
81
|
# Figure out how to report results
|
@@ -98,3 +109,4 @@ class TwitterCrawler
|
|
98
109
|
end
|
99
110
|
end
|
100
111
|
|
112
|
+
|
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: 0.0.6
|
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: 2017-02-07 00:00:00.000000000 Z
|
12
12
|
dependencies: []
|
13
13
|
description: Crawls Twitter
|
14
14
|
email: shidash@shidash.com
|