jim/openai-cookbook
1
0
Fork 0
mirror of https://github.com/james-m-jordan/openai-cookbook.git synced 2025-05-09 19:32:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixed UnicodeEncodeError when writing to file

Browse Source 
This pull request fixes the UnicodeEncodeError that was occurring when writing to a file. Updated the multiple open() calls to specify UTF-8 encoding.
This commit is contained in:
khaled-wsa 2023-02-04 01:55:06 +03:00 committed by GitHub
parent fe448be5e8
commit a7b8506c6e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
solutions/web_crawl_Q&A/web-qa.py
View File

@ -135,7 +135,7 @@ def crawl(url):
print(url) # for debugging and to see the progress
# Save text from the url to a <url>.txt file
with open('text/'+local_domain+'/'+url[8:].replace("/", "_") + ".txt", "w") as f:
with open('text/'+local_domain+'/'+url[8:].replace("/", "_") + ".txt", "w", encoding="utf-8") as f:
# Get the text from the URL using BeautifulSoup
soup = BeautifulSoup(requests.get(url).text, "html.parser")
@ -181,7 +181,7 @@ texts=[]
for file in os.listdir("text/" + domain + "/"):
# Open the file and read the text
with open("text/" + domain + "/" + file, "r") as f:
with open("text/" + domain + "/" + file, "r", encoding="utf-8") as f:
text = f.read()
# Omit the first 11 lines and the last 4 lines, then replace -, _, and #update with spaces.