Adding script to convert tables to csv

Author: abhiramr

Libraries_Tests/Untitled.ipynb

@@ -0,0 +1,108 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import jinja2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from jinja2 import Template"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "t = Template(\"Hello {{ something }}!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "u'Hello World!'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "t.render(something=\"World\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "t = Template(\"My favorite numbers: {% for n in range(1,10) %}{{n}} \" \"{% endfor %}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "u'My favorite numbers: 1 2 3 4 5 6 7 8 9 '"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "t.render()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

Random_Py_scripts/html_tables_to_csv.py

@@ -0,0 +1,35 @@
+import requests
+import pandas as pd
+import numpy as np
+import matplotlib
+import bs4
+from bs4 import BeautifulSoup
+import csv
+import re
+
+
+url = "./1 APR to 15 APR.html" 
+
+def html_tables_to_csv(input_url):
+    soup = BeautifulSoup(open(url).read(), 'html.parser')
+    tables = soup.find_all('table')
+    table = table[3]
+    headers = [(header.text).decode() for header in table.find_all('th')]
+    rows = []
+    for row in table_.find_all('tr'):
+        rows.append([val.text for val in row.find_all('td')])
+
+    rows = [[(x.replace('"', '')).replace('=','').replace(',','').replace(' ','') for x in i] for i in rows]
+
+
+    with open('output_file8.csv', 'w') as f:
+        writer = csv.writer(f)
+        writer.writerow(headers)
+        writer.writerows(row for row in rows if row)
+
+
+def main(url, output_file):
+    html_tables_to_csv(url, output_file)
+
+if __name__ == "__main__":
+	main(sys.argv[1])

Random_Py_scripts/html_tables_to_csv_2.py

@@ -0,0 +1,35 @@
+import requests
+import pandas as pd
+import numpy as np
+import matplotlib
+import bs4
+from bs4 import BeautifulSoup
+import csv
+import re
+
+
+url = "./1 APR to 15 APR.html" 
+
+def html_tables_to_csv(input_url):
+    soup = BeautifulSoup(open(url).read(), 'html.parser')
+    tables = soup.find_all('table')
+    table = table[3]
+    headers = [(header.text).decode() for header in table.find_all('th')]
+    rows = []
+    for row in table_.find_all('tr'):
+        rows.append([val.text for val in row.find_all('td')])
+
+    rows = [[(x.replace('"', '')).replace('=','').replace(',','').replace(' ','') for x in i] for i in rows]
+
+
+    with open('output_file8.csv', 'w') as f:
+        writer = csv.writer(f)
+        writer.writerow(headers)
+        writer.writerows(row for row in rows if row)
+
+
+def main(url, output_file):
+    html_tables_to_csv(url, output_file)
+
+if __name__ == "__main__":
+	main(sys.argv[1])