twitterscraper-ruby 0.16.0 → 0.17.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 66dda5275a9067d328f6637f127895ded954534d304e5e4b349f286a271a08d8
-  data.tar.gz: 6c3ffb3fba82376fc2de49514245ea96c7cb4fa16c32dcd2fff1ab1ae327bd14
+  metadata.gz: ac0c10b18d836983cc6b73e25b9ed333af2f620106a07c6bc6a40058fb127895
+  data.tar.gz: e6fc18219d9127fb30ba57e39dc4656c0f0a3c108428d959de5bac9e7d317088
 SHA512:
-  metadata.gz: 24267284f4f29adc86d5bbe70a30bbe31d6d898546576065f1a9accafc3944a352117bbf6eb0de273743a00fb2d26c5cf37ed016cc0324187a25ca279230d812
-  data.tar.gz: 0bc9f01659560c83b0289bf63119849135b7ec27520dd03c7abd645da99ef660ca4b5fd12301b359cd5cc45a82914d7ceae88ad93ad756fde166718b3d0fe6c2
+  metadata.gz: 90cbf06b606878dc36b4bba44669139c273bf03b08a777ad87036834841bcb4b052e0559813dc56e4be124442abfc5a7fc44c5c9524c74929ca02b1d287d346b
+  data.tar.gz: ada0b74ee42ff62964b73ad9b49358227cdaf4fc87420cf12cf65af95168ad9775615a504345ebc83d3b791e9c0d892691c55bc477eddd647b3e8934f752fb9c

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    twitterscraper-ruby (0.16.0)
+    twitterscraper-ruby (0.17.0)
       nokogiri
       parallel
 

data/README.md

@@ -98,6 +98,7 @@ end
       "screen_name": "@name",
       "name": "Name",
       "user_id": 12340000,
+      "profile_image_url": "https://pbs.twimg.com/profile_images/1826000000/0000.png",
       "tweet_id": 1234000000000000,
       "text": "Thanks Twitter!",
       "links": [],
@@ -122,6 +123,7 @@ end
 - screen_name
 - name
 - user_id
+- profile_image_url
 - tweet_id
 - text
 - links
@@ -173,6 +175,7 @@ Search operators documentation is in [Standard search operators](https://develop
 | `--limit`      | integer | Stop scraping when *at least* the number of tweets indicated with --limit is scraped. | 100 |
 | `--order`      | string  | Sort a order of the results. | desc(default) or asc |
 | `--threads`    | integer | Set the number of threads twitterscraper-ruby should initiate while scraping for your query. | 2 |
+| `--threads_granularity` | string | | auto |
 | `--proxy`      | boolean | Scrape https://twitter.com/search via proxies. | true(default) or false |
 | `--cache`      | boolean | Enable caching. | true(default) or false |
 | `--format`     | string  | The format of the output. | json(default) or html |

data/lib/twitterscraper/cli.rb

@@ -24,6 +24,7 @@ module Twitterscraper
           daily_limit: options['daily_limit'],
           order: options['order'],
           threads: options['threads'],
+          threads_granularity: options['threads_granularity'],
       }
       client = Twitterscraper::Client.new(cache: options['cache'], proxy: options['proxy'])
       tweets = client.query_tweets(options['query'], query_options)
@@ -69,6 +70,7 @@ module Twitterscraper
           'daily_limit:',
           'order:',
           'threads:',
+          'threads_granularity:',
           'output:',
           'format:',
           'cache:',
@@ -82,10 +84,11 @@ module Twitterscraper
       options['lang'] ||= ''
       options['limit'] = (options['limit'] || 100).to_i
       options['daily_limit'] = options['daily_limit'].to_i if options['daily_limit']
-      options['threads'] = (options['threads'] || 2).to_i
+      options['threads'] = (options['threads'] || 10).to_i
+      options['threads_granularity'] ||= 'auto'
       options['format'] ||= 'json'
       options['order'] ||= 'desc'
-      options['output'] ||= "tweets.#{options['format']}"
+      options['output'] ||= build_output_name(options)
 
       options['cache'] = options['cache'] != 'false'
       options['proxy'] = options['proxy'] != 'false'
@@ -93,6 +96,12 @@ module Twitterscraper
       options
     end
 
+    def build_output_name(options)
+      query = ERB::Util.url_encode(options['query'])
+      date = [options['start_date'], options['end_date']].select { |val| val && !val.empty? }.join('_')
+      [options['type'], 'tweets', date, query].compact.join('_') + '.' + options['format']
+    end
+
     def initialize_logger
       Twitterscraper.logger.level = ::Logger::DEBUG if options['verbose']
     end

data/lib/twitterscraper/query.rb

@@ -80,14 +80,14 @@ module Twitterscraper
 
       url = build_query_url(query, lang, type, pos)
       http_request = lambda do
-        logger.debug "Scraping tweets from #{url}"
+        logger.debug "Scraping tweets from url=#{url}"
         get_single_page(url, headers, proxies)
       end
 
       if cache_enabled?
         client = Cache.new
         if (response = client.read(url))
-          logger.debug 'Fetching tweets from cache'
+          logger.debug "Fetching tweets from cache url=#{url}"
         else
           response = http_request.call
           client.write(url, response) unless stop_requested?
@@ -147,21 +147,27 @@ module Twitterscraper
       end
     end
 
-    def build_queries(query, start_date, end_date)
+    def build_queries(query, start_date, end_date, threads_granularity)
       if start_date && end_date
-        # date_range = start_date.upto(end_date - 1)
-        # date_range.map { |date| query + " since:#{date} until:#{date + 1}" }
-
-        queries = []
-        time = Time.utc(start_date.year, start_date.month, start_date.day, 0, 0, 0)
-        end_time = Time.utc(end_date.year, end_date.month, end_date.day, 0, 0, 0)
+        if threads_granularity == 'auto'
+          threads_granularity = start_date.upto(end_date - 1).to_a.size >= 28 ? 'day' : 'hour'
+        end
 
-        while true
-          if time < Time.now.utc
-            queries << (query + " since:#{time.strftime('%Y-%m-%d_%H:00:00')}_UTC until:#{(time + 3600).strftime('%Y-%m-%d_%H:00:00')}_UTC")
+        if threads_granularity == 'day'
+          date_range = start_date.upto(end_date - 1)
+          queries = date_range.map { |date| query + " since:#{date} until:#{date + 1}" }
+        else
+          time = Time.utc(start_date.year, start_date.month, start_date.day, 0, 0, 0)
+          end_time = Time.utc(end_date.year, end_date.month, end_date.day, 0, 0, 0)
+          queries = []
+
+          while true
+            if time < Time.now.utc
+              queries << (query + " since:#{time.strftime('%Y-%m-%d_%H:00:00')}_UTC until:#{(time + 3600).strftime('%Y-%m-%d_%H:00:00')}_UTC")
+            end
+            time += 3600
+            break if time >= end_time
           end
-          time += 3600
-          break if time >= end_time
         end
 
         queries
@@ -209,11 +215,17 @@ module Twitterscraper
       @stop_requested
     end
 
-    def query_tweets(query, type: 'search', start_date: nil, end_date: nil, lang: nil, limit: 100, daily_limit: nil, order: 'desc', threads: 2)
-      start_date = Date.parse(start_date) if start_date && start_date.is_a?(String)
-      end_date = Date.parse(end_date) if end_date && end_date.is_a?(String)
-      queries = build_queries(query, start_date, end_date)
+    def query_tweets(query, type: 'search', start_date: nil, end_date: nil, lang: nil, limit: 100, daily_limit: nil, order: 'desc', threads: 10, threads_granularity: 'auto')
       type = Type.new(type)
+      if type.search?
+        start_date = Date.parse(start_date) if start_date && start_date.is_a?(String)
+        end_date = Date.parse(end_date) if end_date && end_date.is_a?(String)
+      elsif type.user?
+        start_date = nil
+        end_date = nil
+      end
+
+      queries = build_queries(query, start_date, end_date, threads_granularity)
       if threads > queries.size
         threads = queries.size
       end
@@ -228,6 +240,7 @@ module Twitterscraper
 
       validate_options!(queries, type: type, start_date: start_date, end_date: end_date, lang: lang, limit: limit, threads: threads)
 
+      logger.info "The number of queries #{queries.size}"
       logger.info "The number of threads #{threads}"
 
       headers = {'User-Agent': USER_AGENT_LIST.sample, 'X-Requested-With': 'XMLHttpRequest'}
@@ -252,15 +265,17 @@ module Twitterscraper
         end
       end
 
+      logger.info "Return #{@all_tweets.size} tweets"
+
       @all_tweets.sort_by { |tweet| (order == 'desc' ? -1 : 1) * tweet.created_at.to_i }
     end
 
-    def search(query, start_date: nil, end_date: nil, lang: '', limit: 100, daily_limit: nil, order: 'desc', threads: 2)
-      query_tweets(query, type: 'search', start_date: start_date, end_date: end_date, lang: lang, limit: limit, daily_limit: daily_limit, order: order, threads: threads)
+    def search(query, start_date: nil, end_date: nil, lang: '', limit: 100, daily_limit: nil, order: 'desc', threads: 10, threads_granularity: 'auto')
+      query_tweets(query, type: 'search', start_date: start_date, end_date: end_date, lang: lang, limit: limit, daily_limit: daily_limit, order: order, threads: threads, threads_granularity: threads_granularity)
     end
 
     def user_timeline(screen_name, limit: 100, order: 'desc')
-      query_tweets(screen_name, type: 'user', start_date: nil, end_date: nil, lang: nil, limit: limit, daily_limit: nil, order: order, threads: 1)
+      query_tweets(screen_name, type: 'user', start_date: nil, end_date: nil, lang: nil, limit: limit, daily_limit: nil, order: order, threads: 1, threads_granularity: nil)
     end
   end
 end

data/lib/twitterscraper/template.rb

@@ -9,8 +9,8 @@ module Twitterscraper
           chart_data: chart_data(tweets).to_json,
           first_tweet: tweets.sort_by { |t| t.created_at.to_i }[0],
           last_tweet: tweets.sort_by { |t| t.created_at.to_i }[-1],
-          tweets_size: tweets.size,
-          tweets: tweets.take(50)
+          tweets: tweets,
+          convert_limit: 30,
       )
     end
 

data/lib/twitterscraper/template/tweets.html.erb

@@ -1,28 +1,29 @@
 <html>
 <head>
-  <script>
-      window.twttr = (function (d, s, id) {
-          var js, fjs = d.getElementsByTagName(s)[0], t = window.twttr || {};
-          if (d.getElementById(id)) return t;
-          js = d.createElement(s);
-          js.id = id;
-          js.src = "https://platform.twitter.com/widgets.js";
-          fjs.parentNode.insertBefore(js, fjs);
-
-          t._e = [];
-          t.ready = function (f) {
-              t._e.push(f);
-          };
-
-          return t;
-      }(document, "script", "twitter-wjs"));
-  </script>
-
   <script src="https://cdnjs.cloudflare.com/ajax/libs/moment.js/2.27.0/moment.min.js" integrity="sha512-rmZcZsyhe0/MAjquhTgiUcb4d9knaFc7b5xAfju483gbEXTkeJRUMIPk6s3ySZMYUHEcjKbjLjyddGWMrNEvZg==" crossorigin="anonymous"></script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/moment-timezone/0.5.31/moment-timezone-with-data.min.js" integrity="sha512-HZcf3uHWA+Y2P5KNv+F/xa87/flKVP92kUTe/KXjU8URPshczF1Dx+cL5bw0VBGhmqWAK0UbhcqxBbyiNtAnWQ==" crossorigin="anonymous"></script>
   <script src="https://code.highcharts.com/stock/highstock.js"></script>
   <script>
+      function updateTweets() {
+          window.twttr = (function (d, s, id) {
+              var js, fjs = d.getElementsByTagName(s)[0], t = window.twttr || {};
+              if (d.getElementById(id)) return t;
+              js = d.createElement(s);
+              js.id = id;
+              js.src = "https://platform.twitter.com/widgets.js";
+              fjs.parentNode.insertBefore(js, fjs);
+
+              t._e = [];
+              t.ready = function (f) {
+                  t._e.push(f);
+              };
+
+              return t;
+          }(document, "script", "twitter-wjs"));
+      }
+
       function drawChart() {
+          var data = <%= chart_data %>;
           Highcharts.setOptions({
               time: {
                   timezone: moment.tz.guess()
@@ -31,13 +32,13 @@
 
           Highcharts.stockChart('chart', {
               title: {
-                  text: '<%= tweets_size %> tweets of <%= chart_name %>'
+                  text: '<%= tweets.size %> tweets of <%= chart_name %>'
               },
               subtitle: {
-                  text: 'since:<%= first_tweet.created_at.localtime %> until:<%= last_tweet.created_at.localtime %>'
+                  text: 'since:<%= first_tweet.created_at.localtime.strftime('%Y-%m-%d %H:%M') %> until:<%= last_tweet.created_at.localtime.strftime('%Y-%m-%d %H:%M') %>'
               },
               series: [{
-                  data: <%= chart_data %>
+                  data: data
               }],
               rangeSelector: {enabled: false},
               scrollbar: {enabled: false},
@@ -49,6 +50,7 @@
 
       document.addEventListener("DOMContentLoaded", function () {
           drawChart();
+          updateTweets();
       });
   </script>
 
@@ -64,17 +66,31 @@
   </style>
 </head>
 <body>
-<div id="chart"></div>
+<div id="chart" style="width: 100vw; height: 400px;"></div>
 
 <div class="tweets-container">
-  <% tweets.each do |tweet| %>
-    <blockquote class="twitter-tweet">
-      <a href="<%= tweet.tweet_url %>"></a>
-    </blockquote>
-  <% end %>
+  <% tweets.each.with_index do |tweet, i| %>
+    <% tweet_time = tweet.created_at.localtime.strftime('%Y-%m-%d %H:%M') %>
+    <% if i < convert_limit %>
+      <blockquote class="twitter-tweet">
+    <% else %>
+      <div class="twitter-tweet" style="border: 1px solid rgb(204, 214, 221);">
+    <% end %>
+
+    <div style="display: grid; grid-template-rows: 24px 24px; grid-template-columns: 48px 1fr;">
+      <div style="grid-row: 1/3; grid-column:  1/2;"><img src="<%= tweet.profile_image_url %>" width="48" height="48" loading="lazy"></div>
+      <div style="grid-row: 1/2; grid-column:  2/3;"><%= tweet.name %></div>
+      <div style="grid-row: 2/3; grid-column:  2/3;"><a href="https://twitter.com/<%= tweet.screen_name %>">@<%= tweet.screen_name %></a></div>
+    </div>
+
+    <div><%= tweet.text %></div>
+    <div><a href="<%= tweet.tweet_url %>"><small><%= tweet_time %></small></a></div>
 
-  <% if tweets_size > tweets.size %>
-    <div>and more!</div>
+    <% if i < convert_limit %>
+      </blockquote>
+    <% else %>
+      </div>
+    <% end %>
   <% end %>
 </div>
 

data/lib/twitterscraper/tweet.rb

@@ -6,6 +6,7 @@ module Twitterscraper
         :screen_name,
         :name,
         :user_id,
+        :profile_image_url,
         :tweet_id,
         :text,
         :links,
@@ -51,6 +52,11 @@ module Twitterscraper
         end
       end
 
+      # .js-stream-item
+      #   .js-stream-tweet{data: {screen-name:, tweet-id:}}
+      #     .stream-item-header
+      #     .js-tweet-text-container
+      #     .stream-item-footer
       def from_html(text)
         html = Nokogiri::HTML(text)
         from_tweets_html(html.xpath("//li[@class[contains(., 'js-stream-item')]]/div[@class[contains(., 'js-stream-tweet')]]"))
@@ -72,6 +78,8 @@ module Twitterscraper
         end
 
         inner_html = Nokogiri::HTML(html.inner_html)
+
+        profile_image_url = inner_html.xpath("//img[@class[contains(., 'js-action-profile-avatar')]]").first.attr('src').gsub(/_bigger/, '')
         text = inner_html.xpath("//div[@class[contains(., 'js-tweet-text-container')]]/p[@class[contains(., 'js-tweet-text')]]").first.text
         links = inner_html.xpath("//a[@class[contains(., 'twitter-timeline-link')]]").map { |elem| elem.attr('data-expanded-url') }.select { |link| link && !link.include?('pic.twitter') }
         image_urls = inner_html.xpath("//div[@class[contains(., 'AdaptiveMedia-photoContainer')]]").map { |elem| elem.attr('data-image-url') }
@@ -99,6 +107,7 @@ module Twitterscraper
             screen_name: screen_name,
             name: html.attr('data-name'),
             user_id: html.attr('data-user-id').to_i,
+            profile_image_url: profile_image_url,
             tweet_id: tweet_id,
             text: text,
             links: links,

data/lib/version.rb

@@ -1,3 +1,3 @@
 module Twitterscraper
-  VERSION = '0.16.0'
+  VERSION = '0.17.0'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: twitterscraper-ruby
 version: !ruby/object:Gem::Version
-  version: 0.16.0
+  version: 0.17.0
 platform: ruby
 authors:
 - ts-3156