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

Merge pull request #104 from khaled-wsa/patch-3

Browse Source 
Fix UnicodeEncodeError
This commit is contained in:
Logan Kilpatrick 2023-02-06 11:30:48 -06:00 committed by GitHub
commit f6af261085
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

6
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 print(url) # for debugging and to see the progress
# Save text from the url to a <url>.txt file # 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 # Get the text from the URL using BeautifulSoup
soup = BeautifulSoup(requests.get(url).text, "html.parser") soup = BeautifulSoup(requests.get(url).text, "html.parser")
@ -181,7 +181,7 @@ texts=[]
for file in os.listdir("text/" + domain + "/"): for file in os.listdir("text/" + domain + "/"):
# Open the file and read the text # 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() text = f.read()
# Omit the first 11 lines and the last 4 lines, then replace -, _, and #update with spaces. # Omit the first 11 lines and the last 4 lines, then replace -, _, and #update with spaces.
@ -379,4 +379,4 @@ def answer_question(
print(answer_question(df, question="What day is it?", debug=False)) print(answer_question(df, question="What day is it?", debug=False))
print(answer_question(df, question="What is our newest embeddings model?")) print(answer_question(df, question="What is our newest embeddings model?"))