add -o flag

[phrases.git] / extract.py

diff --git a/extract.py b/extract.py
index 322a3020c3eccb18c9ad5c29b8ff9845f81771b8..4e6c1f63544e13e9e434718350714ddd080b9382 100755 (executable)
--- a/extract.py
+++ b/extract.py
@@ -2,55 +2,52 @@
 # Extract Latin famous phrases from wikipedia
 # Armaan Bhojwani 2020
 
-from bs4 import BeautifulSoup
-import requests
+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()
 
-def main():
-    url = 'https://en.wikipedia.org/wiki/List_of_Latin_phrases_(full)'
-    response = requests.get(url)
-    html = response.content
+    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
 
-    soup = BeautifulSoup(html, "html.parser")
-    list_table = soup.find_all("table", attrs={"class":"wikitable"})
-    with open('phrases.csv', 'w') as f:
-        writer = csv.writer(f)
+    with open(args.output, 'w') as f:
+        writer = csv.writer(f, lineterminator="\n")
+
+        # write header
+        headers = ['id', 'Latin', 'English', 'Notes', 'Length']
+        writer.writerow(headers)
 
-        i = 0 # For the phrase id
         # 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.find_all("tr")[1:]:
-                cell = row.find_all("td")
+            for row in table.tbody.find_all("tr", recursive=False):
+                cell = row.find_all("td", recursive=False)
                 rowc = []
 
-                # append phrase id
-                rowc.append(i)
-
-                # avoid out of bounds errors
-                if len(cell) == 2:
-                    lan = 2
-                else:
-                    lan = 3
+                rowc.append(i) # append phrase id
 
                 # add cell content
-                for j in range (0, lan):
-                    content = cell[j]
-                    text=(content.get_text()).rstrip()
+                for content in cell:
+                    text = (content.get_text(" ", strip=True)).rstrip()
                     rowc.append(text)
 
-                # append length of phrase
-                rowc.append(len(rowc[1]))
-                writer.writerow(rowc)
+                if len(rowc) > 1:
+                    rowc.append(len(rowc[1]))
+                    writer.writerow(rowc)
                 i = i + 1
     f.close()
 
-    # Strip empty lines
-    with open('phrases.csv', 'r+') as f:
-        lines = f.readlines()
-        f.seek(0)
-        f.writelines(line for line in lines if line.strip())
-        f.truncate()
-    f.close()
-
 if __name__ == "__main__":
     main()