Charles He answers Database dumps of the EA Forum

[Charles He]

I was trying out OpenAI Codex after getting access this morning and the task of getting EA Forum data seems ideal for testing it out.

Using Codex, I got code that seems like it downloads plain text comments from the forum at the rate of thousands per minute.

It’s a lot faster than writing the script by hand, and does nice things quickly (see time zone fixing).

I thought it was neat!

(This isn’t hardcore code, but in case the OP, or anyone else needs raw forum data, and doesn’t feel like writing the snippets, feel free to comment or send a message.)

Here’s a picture OpenAI interface with the “prompt”:

Actual Code (bottom half generated by OpenAI Codex):

"""
1. Get the last 100 comments from this internet forum  - https://​​forum.effectivealtruism.org/​​graphql
2. Put the contents and createdAt results of the query into a list called comments
4. Clean up the ‘plaintextMainText’ field by removing all formatting extra line returns
5. Save to dataframe and adjust to PST (Pacific Time Zones)
“”″

import pandas as pd
import json
import requests

# Get the last 100 comments from this internet forum  - https://​​forum.effectivealtruism.org/​​graphql

# Use this GraphQL Query
query = “”″
{comments(input: {terms: {view: “recentComments”, limit: 100}}) {
    results {
      _id
      post {
        postedAt
        _id
        title
      }
      user {
        _id
        slug
      }
      contents {
        plaintextMainText
      }
    }
  }
}

“”″

# Put the postedAt and plaintextMainTextinto a list called comments, with error handling for missing values

comments = []

for i in range(0,1):
    print(i)
    url = ′https://​​forum.effectivealtruism.org/​​graphql′
    headers = {‘Content-Type’: ‘application/​json’}
    r = requests.post(url, json={‘query’: query}, headers=headers)
    data = json.loads(r.text)
    for comment in data[‘data’][‘comments’][‘results’]:
        try:
            comments.append([comment[‘post’][‘postedAt’], comment[‘contents’][‘plaintextMainText’]])
        except:
            pass

# Clean up the ‘plaintextMainText’ field by removing all formatting extra line returns

for comment in comments:
    comment[1] = comment[1].replace(‘\n’, ′ ’)

# Save to dataframe and adjust to PST (Pacific Time Zones)

df = pd.DataFrame(comments, columns=[‘postedAt’, ‘plaintextMainText’])
df[‘postedAt’] = pd.to_datetime(df[‘postedAt’])
df[‘postedAt’] = df[‘postedAt’].dt.tz_convert(‘US/​Pacific’)
df[‘postedAt’] = df[‘postedAt’].dt.tz_localize(None)

# Save to csv

df.to_csv(‘effective_altruism_comments.csv’, index=False)

Here’s an example of the output.

Notes:

1. You need to provide a GraphQL query to get Codex to work, it isn’t going to figure it out. A tutorial for creating GraphQL is here. I made a simple query to get comments, as you can see above. The interface for GraphQL seems pretty good and you can create queries to get posts and a lot of other information.

2. I haven’t let this run to try to get the “entire forum”. API/​backend limits or other issues might block this.

3. I can see there’s at least one error in my GraphQL query, I think PostedAt gives a timestamp for the post, not the comment. There’s other typos (I spent 10x more time writing this forum comment than writing the instructions for Codex to generate the code!)