#!/usr/bin/env python3
-# Tool to extract famous phrases from wikipedia
-from bs4 import BeautifulSoup
+# Extract Latin famous phrases from wikipedia
+# Armaan Bhojwani 2020
+
+import argparse
+import sys
+import csv
import requests
+from bs4 import BeautifulSoup
+
+def main(args=sys.argv[1:]):
+ # Argument parsing
+ parser = argparse.ArgumentParser(
+ description="Generate CSV file of Latin famous phrases from Wikipedia.")
+ parser.add_argument("-o", "--output",
+ default="phrases.csv",
+ help="set custom output file location")
+ args = parser.parse_args()
+
+ url = ('https://en.wikipedia.org/w/index.php?title=List_of_Latin_phrases_('
+ 'full)&oldid=986793908')
+ soup = BeautifulSoup(requests.get(url).content, "html.parser")
+ i = 0 # For the phrase id
+
+ with open(args.output, 'w') as f:
+ writer = csv.writer(f, lineterminator="\n")
-url = 'https://en.wikipedia.org/wiki/List_of_Latin_phrases_(full)'
-response = requests.get(url)
-html = response.content
+ # write header
+ headers = ['id', 'Latin', 'English', 'Notes', 'Length']
+ writer.writerow(headers)
-soup = BeautifulSoup(html, "html.parser")
-list_table = soup.find_all("table", attrs={"class":"wikitable"})
+ # iterate through the tables in the page
+ list_table = soup.find_all("table", attrs={"class":"wikitable"})
+ for table in list_table:
+ for row in table.tbody.find_all("tr", recursive=False):
+ cell = row.find_all("td", recursive=False)
+ rowc = []
-output = []
+ rowc.append(i) # append phrase id
-for table in list_table:
- for row in table.find_all("tr")[1:]:
- cell = row.find_all("td")
- for content in cell:
- text = content.get_text()
- output.append(text)
+ # add cell content
+ for content in cell:
+ text = (content.get_text(" ", strip=True)).rstrip()
+ rowc.append(text)
-print(output)
+ if len(rowc) > 1:
+ rowc.append(len(rowc[1]))
+ writer.writerow(rowc)
+ i = i + 1
+ f.close()
+if __name__ == "__main__":
+ main()