first commit

Author: molodsom

.DS_Store

@@ -0,0 +1,25 @@
+name: Save latest data
+on:
+  push:
+    branches:
+      - main
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - uses: actions/setup-python@v2
+      with:
+        python-version: 3.11
+    - run: |
+        python -m pip install --upgrade pip
+        pip install -r requirements.txt
+    - run: python main.py
+    - run: |
+        git config user.email "[email protected]"
+        git config user.name "GitHub Actions"
+        git add output/*
+        git commit -am "Update latest [skip ci]"
+    - uses: ad-m/github-push-action@master
+      with:
+        branch: ${{ github.head_ref }}

.github/workflows/save.yaml

@@ -0,0 +1,2 @@
+.idea/
+venv/

.gitignore

@@ -0,0 +1,3 @@
+# bik
+
+Here I’m just trying to get a list of Russian banks in different formats.

README.md

@@ -0,0 +1,43 @@
+import os
+import cloudscraper
+import zipfile
+import codecs
+import pandas as pd
+from bs4 import BeautifulSoup
+from datetime import datetime, timedelta
+
+urlpath = "https://cbr.ru/vfs/mcirabis/BIKNew/"
+filename = (datetime.now() - timedelta(days=2)).strftime('%Y%m%d') + "ED01OSBR.zip"
+outdir = "output/"
+outzip = outdir + filename
+
+s = cloudscraper.create_scraper(disableCloudflareV1=True, browser="chrome", delay=10)
+
+for _ in range(3):
+    r = s.get(urlpath + filename, allow_redirects=True)
+    if r.status_code != 200:
+        print(f"Error downloading zip: {r.status_code}")
+        continue
+    open(outzip, "wb").write(r.content)
+    break
+
+try:
+    with zipfile.ZipFile(outzip, 'r') as zr:
+        zr.extractall(outdir)
+        os.remove(outzip)
+except Exception as e:
+    print(f"Error unpacking file: {e}")
+    exit(1)
+
+for fp in os.listdir(outdir):
+    if not fp.endswith("_full.xml"):
+        continue
+    with codecs.open(outdir + fp, "r", encoding="windows-1251") as f:
+        content = f.read()
+    s = BeautifulSoup(content, "lxml")
+    df = pd.DataFrame(data=[r.attrs for r in s.findAll("participantinfo")])
+    df.to_csv(outdir + "latest.csv", index=False, header=True)
+    df.to_csv(outdir + "latest.tsv", index=False, header=True, sep="\t", quoting=3)
+    df.to_json(outdir + "latest.json", orient="records")
+    df.to_xml(outdir + "latest.xml")
+    os.remove(outdir + fp)

main.py

@@ -0,0 +1,17 @@
+beautifulsoup4==4.12.2
+certifi==2023.11.17
+charset-normalizer==3.3.2
+cloudscraper==1.2.71
+idna==3.6
+lxml==4.9.3
+numpy==1.26.2
+pandas==2.1.3
+pyparsing==3.1.1
+python-dateutil==2.8.2
+pytz==2023.3.post1
+requests==2.31.0
+requests-toolbelt==1.0.0
+six==1.16.0
+soupsieve==2.5
+tzdata==2023.3
+urllib3==2.1.0