Made code more robust adding try/except

AlbertSuarez · Jul 7, 2019 · b589994 · b589994
1 parent e87d436
commit b589994
Show file tree

Hide file tree

Showing 2 changed files with 44 additions and 34 deletions.
diff --git a/src/azlyrics.py b/src/azlyrics.py
@@ -31,45 +31,54 @@ def _get_html(url):
 def get_artist_url_list(artist_letter):
     artist_url_list = []
 
-    artist_letter_url = f'{AZ_LYRICS_BASE_URL}/{artist_letter}.html'
-    html_content = _get_html(artist_letter_url)
-    if html_content:
-        soup = BeautifulSoup(html_content, 'html.parser')
-
-        column_list = soup.find_all('div', {'class': 'artist-col'})
-        for column in column_list:
-            for a in column.find_all('a'):
-                artist_name = string_cleaner.clean_name(a.text)
-                artist_url = string_cleaner.clean_url('{}/{}'.format(AZ_LYRICS_BASE_URL, a['href']))
-                artist_url_list.append((artist_name, artist_url))
+    try:
+        artist_letter_url = f'{AZ_LYRICS_BASE_URL}/{artist_letter}.html'
+        html_content = _get_html(artist_letter_url)
+        if html_content:
+            soup = BeautifulSoup(html_content, 'html.parser')
+
+            column_list = soup.find_all('div', {'class': 'artist-col'})
+            for column in column_list:
+                for a in column.find_all('a'):
+                    artist_name = string_cleaner.clean_name(a.text)
+                    artist_url = string_cleaner.clean_url('{}/{}'.format(AZ_LYRICS_BASE_URL, a['href']))
+                    artist_url_list.append((artist_name, artist_url))
+    except Exception as e:
+        print(f'Error while getting artists from letter {artist_letter}: {e}')
 
     return artist_url_list
 
 
 def get_song_url_list(artist_url):
     song_url_list = []
 
-    html_content = _get_html(artist_url)
-    if html_content:
-        soup = BeautifulSoup(html_content, 'html.parser')
+    try:
+        html_content = _get_html(artist_url)
+        if html_content:
+            soup = BeautifulSoup(html_content, 'html.parser')
 
-        list_album_div = soup.find('div', {'id': 'listAlbum'})
-        for a in list_album_div.find_all('a'):
-            song_name = string_cleaner.clean_name(a.text)
-            artist_url = string_cleaner.clean_url('{}/{}'.format(AZ_LYRICS_BASE_URL, a['href'].replace('../', '')))
-            song_url_list.append((song_name, artist_url))
+            list_album_div = soup.find('div', {'id': 'listAlbum'})
+            for a in list_album_div.find_all('a'):
+                song_name = string_cleaner.clean_name(a.text)
+                artist_url = string_cleaner.clean_url('{}/{}'.format(AZ_LYRICS_BASE_URL, a['href'].replace('../', '')))
+                song_url_list.append((song_name, artist_url))
+    except Exception as e:
+        print(f'Error while getting songs from artist {artist_url}: {e}')
 
     return song_url_list
 
 
 def get_song_lyrics(song_url):
     song_lyrics = ''
 
-    html_content = _get_html(song_url)
-    if html_content:
-        soup = BeautifulSoup(html_content, 'html.parser')
-        div_list = [div.text for div in soup.find_all('div', {'class': None})]
-        song_lyrics = max(div_list, key=len)
-        song_lyrics = string_cleaner.clean_lyrics(song_lyrics)
+    try:
+        html_content = _get_html(song_url)
+        if html_content:
+            soup = BeautifulSoup(html_content, 'html.parser')
+            div_list = [div.text for div in soup.find_all('div', {'class': None})]
+            song_lyrics = max(div_list, key=len)
+            song_lyrics = string_cleaner.clean_lyrics(song_lyrics)
+    except Exception as e:
+        print(f'Error while getting lyrics from song {song_url}: {e}')
 
     return song_lyrics
diff --git a/src/csv_parser.py b/src/csv_parser.py
@@ -17,12 +17,13 @@ def exists_song(csv_letter, artist_url, song_url):
 
 
 def append_to_csv(artist_name, artist_url, song_name, song_url, song_lyrics, csv_letter):
-    csv_file_name = f'{CSV_FILE}_{csv_letter}.csv'
-    exists_file = os.path.isfile(csv_file_name)
-    with open(csv_file_name, 'a') as file:
-        if not exists_file:
-            file.write(
-                f'"{CSV_HEADER_ARTIST_NAME}","{CSV_HEADER_ARTIST_URL}",'
-                f'"{CSV_HEADER_SONG_NAME}","{CSV_HEADER_SONG_URL}","{CSV_HEADER_LYRICS}"'
-            )
-        file.write(f'\n"{artist_name}","{artist_url}","{song_name}","{song_url}","{song_lyrics}"')
+    if song_lyrics:
+        csv_file_name = f'{CSV_FILE}_{csv_letter}.csv'
+        exists_file = os.path.isfile(csv_file_name)
+        with open(csv_file_name, 'a') as file:
+            if not exists_file:
+                file.write(
+                    f'"{CSV_HEADER_ARTIST_NAME}","{CSV_HEADER_ARTIST_URL}",'
+                    f'"{CSV_HEADER_SONG_NAME}","{CSV_HEADER_SONG_URL}","{CSV_HEADER_LYRICS}"'
+                )
+            file.write(f'\n"{artist_name}","{artist_url}","{song_name}","{song_url}","{song_lyrics}"')