separate a workflow for 4 parallels jobs

This commit is contained in:
Il'ya (Marshal) 2022-05-13 12:42:48 +02:00
parent 9cab070822
commit c79a2f95d4
3 changed files with 59 additions and 25 deletions

View file

@ -19,8 +19,10 @@ jobs:
fail-fast: false
matrix:
mode: [
"0",
"6"
"web",
"web_res",
"server",
"client"
]
steps:
@ -52,19 +54,24 @@ jobs:
python make_files_tree.py
rm -rf __pycache__
- name: Prepare data for mode 0.
if: matrix.mode == '0'
- name: Prepare data.
if: matrix.mode == 'web'
run: |
git checkout data
git pull
mv data/web_res data_ci/web_res
mv data/client data_ci/client
mv data/server data_ci/server
rm -rf data
mv data_ci data
- name: Prepare data for mode 6.
if: matrix.mode == '6'
- name: Prepare data.
if: matrix.mode == 'web_res'
run: |
git checkout data
git pull
mv data/web data_ci/web
mv data/client data_ci/client
@ -73,6 +80,32 @@ jobs:
rm -rf data
mv data_ci data
- name: Prepare data.
if: matrix.mode == 'server'
run: |
git checkout data
git pull
mv data/web data_ci/web
mv data/web_res data_ci/web_res
mv data/client data_ci/client
rm -rf data
mv data_ci data
- name: Prepare data.
if: matrix.mode == 'client'
run: |
git checkout data
git pull
mv data/web data_ci/web
mv data/web_res data_ci/web_res
mv data/server data_ci/server
rm -rf data
mv data_ci data
- name: Commit and push changes.
run: |
git config --global user.email "github-action@users.noreply.github.com"

View file

@ -549,28 +549,36 @@ async def crawl_web_res(session: aiohttp.ClientSession):
await asyncio.gather(*[crawl(url, session, OUTPUT_RESOURCES_FOLDER) for url in tracked_urls])
async def start(mode: int):
async def start(mode: str):
async with aiohttp.ClientSession(connector=CONNECTOR) as session:
# all without web resources
mode == 0 and await asyncio.gather(
mode == 'all' and await asyncio.gather(
crawl_web(session),
crawl_web_res(session),
track_mtproto_configs(),
download_telegram_android_beta_and_extract_resources(session),
download_telegram_macos_beta_and_extract_resources(session),
download_telegram_ios_beta_and_extract_resources(session),
)
mode == 'web' and await asyncio.gather(
crawl_web(session),
)
mode == 'web_res' and await asyncio.gather(
crawl_web_res(session),
)
mode == 'server' and await asyncio.gather(
track_mtproto_configs(),
)
mode == 'client' and await asyncio.gather(
download_telegram_android_beta_and_extract_resources(session),
download_telegram_macos_beta_and_extract_resources(session),
track_mtproto_configs(),
download_telegram_ios_beta_and_extract_resources(session),
)
mode == 1 and await crawl_web(session)
mode == 2 and await download_telegram_android_beta_and_extract_resources(session)
mode == 3 and await download_telegram_macos_beta_and_extract_resources(session)
mode == 4 and await track_mtproto_configs()
mode == 5 and await download_telegram_ios_beta_and_extract_resources(session)
mode == 6 and await crawl_web_res(session)
if __name__ == '__main__':
run_mode = int(sys.argv[1]) if len(sys.argv) > 1 else 0
run_mode = 'all'
if 'MODE' in os.environ:
run_mode = int(os.environ['MODE'])
run_mode = os.environ['MODE']
start_time = time()
logger.info(f'Start crawling content of tracked urls...')

View file

@ -1,7 +0,0 @@
#!/bin/bash
python make_files_tree.py > /dev/null 1 &
python make_files_tree.py > /dev/null 2 &
python make_files_tree.py > /dev/null 3 &
python make_files_tree.py > /dev/null 4 &
wait