Duplicate from Davis/twitter_scraper

Co-authored-by: Davis David <Davis@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,47 @@
+---
+title: Twitter_scraper
+emoji: 🐠
+colorFrom: purple
+colorTo: red
+sdk: streamlit
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: Davis/twitter_scraper
+---
+
+# Configuration
+
+`title`: _string_
+Display title for the Space
+
+`emoji`: _string_
+Space emoji (emoji-only character allowed)
+
+`colorFrom`: _string_
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`colorTo`: _string_
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`sdk`: _string_
+Can be either `gradio`, `streamlit`, or `static`
+
+`sdk_version` : _string_
+Only applicable for `streamlit` SDK.  
+See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
+
+`app_file`: _string_
+Path to your main application file (which contains either `gradio` or `streamlit` Python code, or `static` html code).
+Path is relative to the root of the repository.
+
+`models`: _List[string]_
+HF model IDs (like "gpt2" or "deepset/roberta-base-squad2") used in the Space.
+Will be parsed automatically from your code if not specified here.
+
+`datasets`: _List[string]_
+HF dataset IDs (like "common_voice" or "oscar-corpus/OSCAR-2109") used in the Space.
+Will be parsed automatically from your code if not specified here.
+
+`pinned`: _boolean_
+Whether the Space stays on top of your list.

app.py

@@ -0,0 +1,65 @@
+import streamlit as st
+import twint
+import pandas as pd
+
+
+# add banner image
+st.header("Data Scraper App")
+st.image('twitter.jpg')
+st.subheader('''
+A simple app to scrap data from Twitter.
+''')
+
+# form to collect searcy query and other conditions
+my_form = st.form(key='Twitter_form')
+search_query = my_form.text_input('Input your search query')
+data_limit = my_form.slider('How many tweets do you want to get?', 
+                    10, 
+                    3000, 
+                    value= 100,
+                    step=10)
+
+output_csv = my_form.radio('Save data to a CSV file?', 
+                        ['Yes', 'No'])
+file_name = my_form.text_input('Name the CSV file:')
+submit = my_form.form_submit_button(label='Search')
+
+# function to show output in pandas dataframe with specific folumns 
+def twint_to_pd(columns):
+  return twint.output.panda.Tweets_df[columns]
+
+# configure twint to serach the query
+if submit:
+    config = twint.Config()
+    config.Search = search_query
+    config.Limit = data_limit
+    config.Pandas = True
+    if output_csv == "Yes":
+        config.Store_csv = True
+        config.Output = '{}.csv'.format(file_name)
+    twint.run.Search(config)
+
+    st.subheader("Results: Sample Data")
+    if output_csv == "Yes":
+        # show data in pandas dataframe
+        data = pd.read_csv('{}.csv'.format(file_name),usecols=['date','username','tweet'])
+        st.table(data)
+    else:
+        data = twint_to_pd(["date","username","tweet"])
+        st.table(data)
+        
+    
+    #download the dataframe
+    @st.cache
+    def convert_df(df):
+        # IMPORTANT: Cache the conversion to prevent computation on every rerun
+        return df.to_csv().encode('utf-8')
+
+    csv = convert_df(data)
+
+    st.download_button(
+        label="Download scrapped data as CSV",
+        data=csv,
+        file_name='{}.csv'.format(file_name),
+        mime='text/csv',
+ )

requirements.txt

@@ -0,0 +1,3 @@
+pandas==1.2.5
+streamlit==1.2.0
+twint==2.1.20