twitterscraper-ruby 0.8.0 → 0.9.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5a0a2d55fac0a72e83d696c088daa6ca84b7b13519fbbe7a259dd1979373039a
-  data.tar.gz: a6cf2a0793f05d03d8d9b489eba985a244c7dce9f70e935d03207a7e103d6365
+  metadata.gz: 59b71fc6129f6d8c5a441981dc1577fa9b761380ff119bed4985cfcd88ccb31b
+  data.tar.gz: 2de3fcadc334ee2689d3083ea9324127c3b22ec94cf1b08dec920f9c95771445
 SHA512:
-  metadata.gz: 3b4ca939b22a48fc53e1c1cb9ea25f55cdd6f8a53eb26fa1733948a8df44cd46fa51884668a70bbc31e85c4b986172d23995633557644b5ea93d7640b4034cf9
-  data.tar.gz: 9b1d61933990c916734fc6722bc12e6fdda513c4532edcb86982feabc30dabeaa13f39db03c8555fb8ddaa2aafc0493cb88069fbc374515737ed1465522f153b
+  metadata.gz: b1e392bc021f6f758b79b7bdcd099af2ac391863f8712dadb5fd19248946867cfd89f140b836532fb40554c82697b26ef3af00b7cbb2cb13b0d5a8e2a38c87e7
+  data.tar.gz: 8c0e81589202e4a094c17604354f0f23a08b4536fe60b58ffe616cf1233c0531547ef02b8e88b6f70b1870ce2d134e4518ee093a5349144e2edfce3b1088e06c

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    twitterscraper-ruby (0.8.0)
+    twitterscraper-ruby (0.9.0)
       nokogiri
       parallel
 

data/README.md

@@ -56,12 +56,60 @@ tweets = client.query_tweets(KEYWORD, options)
 tweets.each do |tweet|
   puts tweet.tweet_id
   puts tweet.text
-  puts tweet.created_at
   puts tweet.tweet_url
+  puts tweet.created_at
+
+  hash = tweet.attrs
+  puts hash.keys
 end
 ```
 
 
+## Attributes
+
+### Tweet
+
+- screen_name
+- name
+- user_id
+- tweet_id
+- text
+- links
+- hashtags
+- image_urls
+- video_url
+- has_media
+- likes
+- retweets
+- replies
+- is_replied
+- is_reply_to
+- parent_tweet_id
+- reply_to_users
+- tweet_url
+- created_at
+
+
+## Search operators
+
+| Operator | Finds Tweets... |
+| ------------- | ------------- |
+| watching now | containing both "watching" and "now". This is the default operator. |
+| "happy hour" | containing the exact phrase "happy hour". |
+| love OR hate | containing either "love" or "hate" (or both). |
+| beer -root | containing "beer" but not "root". |
+| #haiku | containing the hashtag "haiku". |
+| from:interior | sent from Twitter account "interior". |
+| to:NASA | a Tweet authored in reply to Twitter account "NASA". |
+| @NASA | mentioning Twitter account "NASA". |
+| puppy filter:media | containing "puppy" and an image or video. |
+| puppy -filter:retweets | containing "puppy", filtering out retweets |
+| superhero since:2015-12-21 | containing "superhero" and sent since date "2015-12-21" (year-month-day). |
+| puppy until:2015-12-21 | containing "puppy" and sent before the date "2015-12-21". |
+
+Search operators documentation is in [Standard search operators](https://developer.twitter.com/en/docs/tweets/rules-and-filtering/overview/standard-operators).
+
+
 ## Examples
 
 ```shell script
@@ -79,27 +127,10 @@ $ cat tweets.json | jq . | less
     "tweet_url": "https://twitter.com/screenname/status/1282659891992000000",
     "created_at": "2020-07-13 12:00:00 +0000",
     "text": "Thanks Twitter!"
-  },
-  ...
+  }
 ]
 ```
 
-## Attributes
-
-### Tweet
-
-- tweet_id
-- text
-- user_id
-- screen_name
-- name
-- links
-- hashtags
-- image_urls
-- tweet_url
-- created_at
-
-
 ## CLI Options
 
 | Option | Description | Default |

data/lib/twitterscraper/cli.rb

@@ -25,7 +25,7 @@ module Twitterscraper
       }
       client = Twitterscraper::Client.new
       tweets = client.query_tweets(options['query'], query_options)
-      File.write(options['output'], generate_json(tweets))
+      File.write(options['output'], generate_json(tweets)) unless tweets.empty?
     end
 
     def generate_json(tweets)

data/lib/twitterscraper/query.rb

@@ -97,7 +97,7 @@ module Twitterscraper
       end
     end
 
-    OLDEST_DATE = Date.parse('2006-3-21')
+    OLDEST_DATE = Date.parse('2006-03-21')
 
     def validate_options!(query, start_date:, end_date:, lang:, limit:, threads:, proxy:)
       if query.nil? || query == ''

data/lib/twitterscraper/tweet.rb

@@ -21,6 +21,7 @@ module Twitterscraper
         :parent_tweet_id,
         :reply_to_users,
         :tweet_url,
+        :timestamp,
         :created_at,
     ]
     attr_reader *KEYS
@@ -31,10 +32,14 @@ module Twitterscraper
       end
     end
 
-    def to_json(options = {})
+    def attrs
       KEYS.map do |key|
         [key, send(key)]
-      end.to_h.to_json
+      end.to_h
+    end
+
+    def to_json(options = {})
+      attrs.to_json
     end
 
     class << self
@@ -74,7 +79,7 @@ module Twitterscraper
           reply_to_users = inner_html.xpath("//div[@class[contains(., 'ReplyingToContextBelowAuthor')]]/a").map { |user| {screen_name: user.text.delete_prefix('@'), user_id: user.attr('data-user-id')} }
         end
 
-        timestamp = inner_html.xpath("//span[@class[contains(., 'ProfileTweet-action--favorite')]]").first.attr('data-time').to_i
+        timestamp = inner_html.xpath("//span[@class[contains(., 'js-short-timestamp')]]").first.attr('data-time').to_i
         new(
             screen_name: html.attr('data-screen-name'),
             name: html.attr('data-name'),
@@ -94,6 +99,7 @@ module Twitterscraper
             parent_tweet_id: parent_tweet_id,
             reply_to_users: reply_to_users,
             tweet_url: 'https://twitter.com' + html.attr('data-permalink-path'),
+            timestamp: timestamp,
             created_at: Time.at(timestamp, in: '+00:00'),
         )
       end

data/lib/version.rb

@@ -1,3 +1,3 @@
 module Twitterscraper
-  VERSION = '0.8.0'
+  VERSION = '0.9.0'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: twitterscraper-ruby
 version: !ruby/object:Gem::Version
-  version: 0.8.0
+  version: 0.9.0
 platform: ruby
 authors:
 - ts-3156