OpenSource/telegram-crawler
OpenSource/telegram-crawler
1
0
Fork 0
mirror of https://github.com/MarshalX/telegram-crawler.git synced 2024-11-26 01:07:37 +01:00
Code Issues Projects Releases Packages Wiki Activity

the end.

Browse source
This commit is contained in:
Il'ya (Marshal) 2021-04-23 21:47:15 +02:00
parent 5ddd778e2e
commit 4a422db809
2 changed files with 6 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
.github/workflows/make_tracked_links_list.yml vendored
View file

@ -27,17 +27,17 @@ jobs:
pip install -r requirements.txt pip install -r requirements.txt
- name: Generate/update file with links. - name: Generate/update file with links.
env:
OUTPUT_FILENAME: "tracked_links_ci.txt"
run: | run: |
python make_tracked_links_list.py python make_tracked_links_list.py
- name: Commit and push changes. - name: Commit and push changes.
run: | run: |
git pull git pull
git add .
git stash
git checkout data git checkout data
git stash pop
mv tracked_links_ci.txt tracked_links.txt
git config --global user.email "github-action@users.noreply.github.com" git config --global user.email "github-action@users.noreply.github.com"
git config --global user.name "GitHub Action" git config --global user.name "GitHub Action"

3
make_tracked_links_list.py
View file

@ -1,3 +1,4 @@
import os
import asyncio import asyncio
import logging import logging
import re import re
@ -45,7 +46,7 @@ RELATIVE_LINK_REGEX = r'\/([-a-zA-Z0-9\/@:%._\+~#]{0,249})'
DOM_ATTRS = ['href', 'src'] DOM_ATTRS = ['href', 'src']
OUTPUT_FILENAME = 'tracked_links.txt' OUTPUT_FILENAME = os.environ.get('OUTPUT_FILENAME', 'tracked_links.txt')
# unsecure but so simple # unsecure but so simple
CONNECTOR = aiohttp.TCPConnector(ssl=False) CONNECTOR = aiohttp.TCPConnector(ssl=False)