add csv

lzjun567 · lzjun567 · commit 30c8952b0f00 · 2017-03-02T17:59:43.000+08:00
diff --git a/juejin/anay.py b/juejin/anay.py
@@ -1,14 +1,11 @@
 import pandas as pd
 
-# &#21152;&#36733;&#25968;&#25454;
-tag_df = pd.read_csv('D:/my/crawler_html2pdf/juejin/tag.csv')
+tags_df = pd.read_csv('D:/my/crawler_html2pdf/juejin/tag.csv')
 
-# &#25490;&#24207;
-sorted_tags = tag_df.sort_values(by=['viewsCount'], ascending=False)
-languages = ['Android', 'iOS', 'Java', 'Python', 'Ruby', 'Swift', 'Go', 'Dart', 'Objective-C', 'C', 'C++', 'C#', 'PHP',
-             'JavaScript', 'Perl', 'VB', 'R', 'MATLAB', 'Groovy', "Scala"]
+languages = ['Java', 'Python', 'Ruby', 'Swift', 'Go', 'Dart', 'Objective-C', 'C', 'C++', 'C#', 'PHP', 'JavaScript',
+             'Perl', 'VB', 'R', 'MATLAB', 'Groovy', "Scala"]
 
-lang_tags = sorted_tags[sorted_tags["title"].isin(languages)]
+lang_tags_df = tags_df[tags_df["title"].isin(languages)]
 
 lang_tags = lang_tags[['title', 'viewsCount']]
 lang_tags.drop(177, axis=0, inplace=True)
diff --git a/juejin/js_tag.csv b/juejin/js_tag.csv
@@ -0,0 +1,10 @@
+,collectionsCount,subscribersCount,entriesCount,viewsCount
+d3.js,688,6128,11,8974
+Meteor.js,848,4493,24,19344
+Ember.js,260,3455,10,11782
+Angular.js,15692,28530,230,318873
+Backbone.js,151,5821,5,3978
+React.js,47617,45185,726,915804
+Vue.js,68222,39886,730,1403066
+Underscore.js,399,4270,12,7084
+Sea.js,397,6461,7,6001
diff --git a/juejin/lang_tag.csv b/juejin/lang_tag.csv
@@ -0,0 +1,12 @@
+,collectionsCount,subscribersCount,entriesCount,viewsCount
+Python,45234,45100,1007,930588
+C,2213,14870,50,52019
+PHP,15376,25143,375,329720
+C++,3495,18404,101,75019
+Go,5321,12881,179,145851
+Ruby,1543,6711,40,45162
+Java,103821,65303,1493,1590201
+Scala,282,3928,17,7468
+Swift,28498,30317,1180,928488
+Objective-C,12250,24198,337,282144
+JavaScript,222100,88872,2412,3548736
