From e8e60427646cf8e88e67fe4f6af6af1d59c35488 Mon Sep 17 00:00:00 2001
From: Jimmy Ho <jimmyho@yelp.com>
Date: Thu, 25 Apr 2024 22:03:13 -0400
Subject: [PATCH 1/3] Updated .gitignore and requirements.txt.

---
 .gitignore       |  3 ++-
 requirements.txt | 29 ++++++++++++++++++++++++-----
 2 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/.gitignore b/.gitignore
index 7b7e21a..11910e1 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,2 +1,3 @@
 local.py
-.vscode/*
\ No newline at end of file
+.vscode/*
+venv/*
diff --git a/requirements.txt b/requirements.txt
index 570b153..3e1f244 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,5 +1,24 @@
-certifi==2020.12.5
-chardet==4.0.0
-idna==2.10
-requests==2.25.1
-urllib3==1.26.2
+beautifulsoup4==4.12.3
+certifi==2024.2.2
+charset-normalizer==3.3.2
+idna==3.7
+ioutil==1.0.3
+local==1.0.0
+lyricsgenius==3.0.1
+numpy==1.26.4
+pandas==2.2.2
+pyarrow==16.0.0
+pyperclip==1.8.2
+python-dateutil==2.9.0.post0
+pytz==2024.1
+requests==2.31.0
+Send2Trash==1.8.3
+six==1.16.0
+soupsieve==2.5
+speedtest-cli==2.1.3
+srutil==1.0.3
+tabulate==0.9.0
+toml==0.10.2
+tzdata==2024.1
+urllib3==2.2.1
+wikipedia==1.4.0

From 1fcddd42ab388e6537bb685a7961184bb8259095 Mon Sep 17 00:00:00 2001
From: Jimmy Ho <jimmyho@yelp.com>
Date: Thu, 25 Apr 2024 22:44:34 -0400
Subject: [PATCH 2/3] Updated scraper.py to refine special characters handling.

---
 scraper.py | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/scraper.py b/scraper.py
index 08ac1ad..3cc6f63 100644
--- a/scraper.py
+++ b/scraper.py
@@ -119,6 +119,7 @@
 LYRIC_JSON_PATH = 'lyrics.json'
 SONG_LIST_PATH = 'song_titles.txt'
 
+access_token = # put your genius.com API access token here as a string
 
 def main():
     parser = argparse.ArgumentParser()
@@ -239,7 +240,7 @@ def albums_to_songs_csv(songs_by_album, existing_df=None):
             for song in songs_by_album[album]:
                 if song.title not in IGNORE_SONGS and song.title not in songs_titles:
                     record = {
-                        'Title': song.title.strip('\u200b'),
+                        'Title': song.title.replace('\u200b', ''),
                         'Album':
                         album if 'Lover (Target' not in album else 'Lover',
                         'Lyrics': song.lyrics,
@@ -250,7 +251,7 @@ def albums_to_songs_csv(songs_by_album, existing_df=None):
             for song in songs_by_album[album]:
                 if song in OTHER_SONGS and song.title not in songs_titles:
                     record = {
-                        'Title': song.title,
+                        'Title': song.title.replace('\u200b', ''),
                         'Album': album,
                         'Lyrics': song.lyrics,
                     }
@@ -376,8 +377,12 @@ def clean_lyrics(lyrics: str) -> str:
     lyrics = re.sub(r'\u201C|\u201D', '"', lyrics)
     # Replace special unicode spaces with standard space
     lyrics = re.sub(
-        r'[\u00A0\u1680​\u180e\u2000-\u2009\u200a​\u200b​\u202f\u205f​\u3000]',
+        r'[\u00A0\u1680​\u180e\u2000-\u2009\u200a​\u202f\u205f​\u3000]',
         " ", lyrics)
+    # Replace zero-width space with empty string
+    lyrics = lyrics.replace('\u200b', '')
+    # Replace Cyrillic 'e' letters with English 'e'.
+    lyrics = re.sub(r'\u0435', "e", lyrics)
     # Replace dashes with space and single hyphen
     lyrics = re.sub(r'\u2013|\u2014', " - ", lyrics)
     # Replace hyperlink text

From b9ea6a859c1d304c33d80f4230266594927849f1 Mon Sep 17 00:00:00 2001
From: Jimmy Ho <jimmyho@yelp.com>
Date: Fri, 26 Apr 2024 18:02:36 -0400
Subject: [PATCH 3/3] Updates to address PR comments.

---
 .gitignore | 3 +--
 scraper.py | 1 -
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/.gitignore b/.gitignore
index 11910e1..7b7e21a 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,2 @@
 local.py
-.vscode/*
-venv/*
+.vscode/*
\ No newline at end of file
diff --git a/scraper.py b/scraper.py
index 3cc6f63..1e7f79d 100644
--- a/scraper.py
+++ b/scraper.py
@@ -119,7 +119,6 @@
 LYRIC_JSON_PATH = 'lyrics.json'
 SONG_LIST_PATH = 'song_titles.txt'
 
-access_token = # put your genius.com API access token here as a string
 
 def main():
     parser = argparse.ArgumentParser()