Skip to content

Make the _get_gql_ops.py way faster by keeping connection alive #264

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Make the _get_gql_ops.py way faster by keeping connection alive #264

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
240273c
Update _get_gql_ops.py
kedihacker Jun 11, 2025
182d641
Update _get_gql_ops.py
kedihacker Jun 11, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 17 additions & 16 deletions _get_gql_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,29 +24,30 @@ async def get_scripts():
]

scripts = []
for i, x in enumerate(urls, 1):
cache_path = os.path.join(cache_dir, x.split("/")[-1].split("?")[0])
if os.path.exists(cache_path):
with open(cache_path) as fp:
scripts.append(fp.read())
continue

print(f"({i:3d} / {len(urls):3d}) {x}")
rep = await httpx.AsyncClient().get(x)
rep.raise_for_status()

with open(cache_path, "w") as fp:
fp.write(rep.text)
scripts.append(rep.text)
async with httpx.AsyncClient() as clit:
for i, x in enumerate(urls, 1):
cache_path = os.path.join(cache_dir, x.split("/")[-1].split("?")[0])
if os.path.exists(cache_path):
with open(cache_path) as fp:
scripts.append(fp.read())
continue

print(f"({i:3d} / {len(urls):3d}) {x}")
rep = await clit.get(x)
rep.raise_for_status()

with open(cache_path, "w") as fp:
fp.write(rep.text)
scripts.append(rep.text)

return scripts


async def main():
with open("./twscrape/api.py") as fp:

with open("./twscrape/api.py") as fp:
ops = [x.strip() for x in fp.read().split("\n")]
ops = [x.split("=")[0].removeprefix("OP_").strip() for x in ops if x.startswith("OP_")]

all_pairs = {}
for txt in await get_scripts():
pairs = re.findall(r'queryId:"(.+?)".+?operationName:"(.+?)"', txt)
Expand Down