diff --git a/govscape/pyproject.toml b/govscape/pyproject.toml index 369d1abb..90b17dbb 100644 --- a/govscape/pyproject.toml +++ b/govscape/pyproject.toml @@ -2,7 +2,7 @@ name = "govscape" version = "0.1.0" description = "" -authors = ["kylebd99 "] +authors = [] readme = "README.md" diff --git a/govscape_conf b/govscape_conf index 3bac3c0d..0eb51540 100644 --- a/govscape_conf +++ b/govscape_conf @@ -1,12 +1,12 @@ server { - server_name govscape.net www.govscape.net; + server_name govscape-anonymized.net www.govscape-anonymized.net; root /home/ubuntu/govscape/interface/build; index index.html; # Redirect all www requests to non-www requests - if ($host = www.govscape.net) { - return 301 https://govscape.net$request_uri; + if ($host = www.govscape-anonymized.net) { + return 301 https://govscape-anonymized.net$request_uri; } # Serve static frontend files @@ -30,26 +30,25 @@ server { listen 443 ssl; # HTTPS port - # SSL configuration (managed by Certbot) - ssl_certificate /etc/letsencrypt/live/govscape.net/fullchain.pem; - ssl_certificate_key /etc/letsencrypt/live/govscape.net/privkey.pem; - include /etc/letsencrypt/options-ssl-nginx.conf; - ssl_dhparam /etc/letsencrypt/ssl-dhparams.pem; + ssl_certificate /etc/letsencrypt/live/govscape-anonymized.net/fullchain.pem; # managed by Certbot + ssl_certificate_key /etc/letsencrypt/live/govscape-anonymized.net/privkey.pem; # managed by Certbot + include /etc/letsencrypt/options-ssl-nginx.conf; # managed by Certbot + ssl_dhparam /etc/letsencrypt/ssl-dhparams.pem; # managed by Certbot } # HTTP server block: redirect to HTTPS server { listen 80; - server_name govscape.net www.govscape.net; + server_name govscape-anonymized.net www.govscape-anonymized.net; - # Redirect all HTTP requests to HTTPS - if ($host = www.govscape.net) { - return 301 https://govscape.net$request_uri; - } + if ($host = www.govscape-anonymized.net) { + return 301 https://$host$request_uri; + } # managed by Certbot - if ($host = govscape.net) { - return 301 https://$host$request_uri; - } + + if ($host = govscape-anonymized.net) { + return 301 https://$host$request_uri; + } # managed by Certbot return 404; # fallback } \ No newline at end of file diff --git a/interface/src/lib/components/CookieConsent.svelte b/interface/src/lib/components/CookieConsent.svelte deleted file mode 100644 index 801544fd..00000000 --- a/interface/src/lib/components/CookieConsent.svelte +++ /dev/null @@ -1,173 +0,0 @@ - - -{#if show} - -{/if} - - diff --git a/interface/src/lib/utils/fetch.js b/interface/src/lib/utils/fetch.js index d3189f84..85c4946d 100644 --- a/interface/src/lib/utils/fetch.js +++ b/interface/src/lib/utils/fetch.js @@ -6,7 +6,7 @@ const ENDPOINTS = { S3: 'http://localhost:8080/img' }, PROD: { - API: 'https://govscape.net/api', + API: 'https://govscape-anonymized.net/api', S3: 'https://bcgl-public-bucket.s3.amazonaws.com/prod-serving/img' } }; diff --git a/interface/src/routes/+layout.svelte b/interface/src/routes/+layout.svelte index afd18dcc..ff86066e 100644 --- a/interface/src/routes/+layout.svelte +++ b/interface/src/routes/+layout.svelte @@ -1,21 +1,5 @@
@@ -23,22 +7,10 @@ - {#key $page.url.pathname} {/key} -
- -
-
diff --git a/scripts/python_helpers/retrieve_pdfs.py b/scripts/python_helpers/retrieve_pdfs.py index 8652025f..71593cb7 100644 --- a/scripts/python_helpers/retrieve_pdfs.py +++ b/scripts/python_helpers/retrieve_pdfs.py @@ -32,7 +32,7 @@ def retrieve_and_store_pdfs(pdf_warc_files, local_dir, output_bucket_name, outpu start_time = time.time() for filename in pdf_warc_files: s3_url = f'https://eotarchive.s3.amazonaws.com/{filename}' - myagent = 'govscape/0.1 (PDF Retrieval Script; kdeeds@cs.washington.edu)' + myagent = 'govscape/0.1 (PDF Retrieval Script)' try: # Send the HTTP GET request to the S3 URL with the specified byte range diff --git a/scripts/python_helpers/retrieve_pdfs_2020_one_off.py b/scripts/python_helpers/retrieve_pdfs_2020_one_off.py index ab7f4164..5f826b43 100644 --- a/scripts/python_helpers/retrieve_pdfs_2020_one_off.py +++ b/scripts/python_helpers/retrieve_pdfs_2020_one_off.py @@ -35,7 +35,7 @@ def retrieve_and_store_pdfs(file_batch, idx, output_bucket_name, output_director length = int(file_batch.iloc[i]['length']) offset = int(file_batch.iloc[i]['offset']) s3_url = f'https://eotarchive.s3.amazonaws.com/{filename}' - myagent = 'govscape/0.1 (PDF Retrieval Script; kdeeds@cs.washington.edu)' + myagent = 'govscape/0.1 (PDF Retrieval Script)' byte_range = f'bytes={offset}-{offset + length - 1}' object_exists = False