367 lines
19 KiB
Python
Executable File
367 lines
19 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""Extract AppsFlyer click-gap reports and publish validated static JSON."""
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import datetime as dt
|
|
import json
|
|
import logging
|
|
import math
|
|
import os
|
|
import re
|
|
import shutil
|
|
import sqlite3
|
|
import subprocess
|
|
import sys
|
|
import tempfile
|
|
import time
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
DB_PATH = "/Users/ads-center/Documents/database/af_click_gap.db"
|
|
PID = "shareit"
|
|
CLICK_NUM = 300
|
|
REPORT_COLUMNS = ["dt", "attr_platform", "pkg_name", "shareit_clicks", "af_clicks", "installs_ua", "clicks_diff", "clicks_diff_rate"]
|
|
SPECIAL_PKGS = {
|
|
"za.co.freeurl.easybetapp.fwdb": "za.co.freeurl.easybetapp.fwdb-Shareit",
|
|
"org.melbet.client": "org.melbet.client-Custom", "org.xbet.client1": "org.xbet.client1-Custom",
|
|
"org.betwinner_ng.client": "org.betwinner_ng.client-Custom", "org.betwinner_zm.client": "org.betwinner_zm.client-Custom",
|
|
"org.betwinner_cm.client": "org.betwinner_cm.client-Custom", "org.betwinner_cd.client": "org.betwinner_cd.client-Custom",
|
|
}
|
|
EXPECTED_TYPES = {"pid": "TEXT", "dt": "TEXT", "attr_platform": "TEXT", "pkg_name": "TEXT", "shareit_clicks": "REAL", "af_clicks": "REAL", "installs_ua": "REAL", "clicks_diff": "REAL", "clicks_diff_rate": "REAL", "updated_at": "TEXT"}
|
|
LOG_PATH = Path(os.path.expanduser("~/Library/Logs/af-click-gap/pipeline.log"))
|
|
|
|
|
|
def logger_setup() -> logging.Logger:
|
|
LOG_PATH.parent.mkdir(parents=True, exist_ok=True)
|
|
log = logging.getLogger("af_click_gap")
|
|
if not log.handlers:
|
|
log.setLevel(logging.INFO)
|
|
handler = logging.FileHandler(LOG_PATH, encoding="utf-8")
|
|
handler.setFormatter(logging.Formatter("%(asctime)s %(levelname)s %(message)s"))
|
|
log.addHandler(handler)
|
|
log.addHandler(logging.StreamHandler())
|
|
return log
|
|
|
|
|
|
LOG = logger_setup()
|
|
|
|
|
|
def date8(value: str) -> str:
|
|
try:
|
|
parsed = dt.datetime.strptime(value, "%Y%m%d")
|
|
except ValueError as exc:
|
|
raise ValueError(f"非法日期: {value}") from exc
|
|
return parsed.strftime("%Y%m%d")
|
|
|
|
|
|
def date8_from_iso(value: str) -> str:
|
|
try:
|
|
return dt.datetime.strptime(value, "%Y-%m-%d").strftime("%Y%m%d")
|
|
except ValueError as exc:
|
|
raise ValueError(f"日期必须为 YYYY-MM-DD: {value}") from exc
|
|
|
|
|
|
def window(start: str | None, end: str | None) -> tuple[str, str]:
|
|
today = dt.date.today()
|
|
if start is None and end is None:
|
|
first, last = today - dt.timedelta(days=6), today
|
|
else:
|
|
if not start or not end:
|
|
raise ValueError("--start-date 与 --end-date 必须同时提供")
|
|
first = dt.datetime.strptime(start, "%Y-%m-%d").date()
|
|
last = dt.datetime.strptime(end, "%Y-%m-%d").date()
|
|
if first > last or (last - first).days > 6:
|
|
raise ValueError("日期区间必须为包含首尾且不超过 7 天")
|
|
return first.strftime("%Y%m%d"), last.strftime("%Y%m%d")
|
|
|
|
|
|
def finite_number(value: Any, field: str, allow_null: bool = False) -> int | float | None:
|
|
if value is None or (isinstance(value, float) and math.isnan(value)):
|
|
if allow_null:
|
|
return None
|
|
raise ValueError(f"{field} 不能为空")
|
|
try:
|
|
number = float(value)
|
|
except (TypeError, ValueError) as exc:
|
|
raise ValueError(f"{field} 必须为数值") from exc
|
|
if not math.isfinite(number):
|
|
raise ValueError(f"{field} 必须为有限数值")
|
|
return int(number) if number.is_integer() else number
|
|
|
|
|
|
def validate_existing_schema(path: str) -> None:
|
|
db = Path(path)
|
|
if not db.is_file():
|
|
raise RuntimeError(f"SQLite 文件不存在: {path}")
|
|
try:
|
|
with sqlite3.connect(f"file:{db}?mode=ro", uri=True) as conn:
|
|
columns = conn.execute("PRAGMA table_info(click_gap)").fetchall()
|
|
except sqlite3.Error as exc:
|
|
raise RuntimeError(f"SQLite 不可读: {exc}") from exc
|
|
if not columns:
|
|
raise RuntimeError("click_gap 表不存在")
|
|
by_name = {row[1]: row for row in columns}
|
|
missing = set(EXPECTED_TYPES) - set(by_name)
|
|
if missing:
|
|
raise RuntimeError(f"click_gap 缺少列: {sorted(missing)}")
|
|
for name, expected in EXPECTED_TYPES.items():
|
|
if str(by_name[name][2]).upper() != expected:
|
|
raise RuntimeError(f"click_gap 列类型不兼容: {name}")
|
|
if [(row[1], row[5]) for row in columns if row[5]] != [("pid", 1), ("dt", 2), ("pkg_name", 3)]:
|
|
raise RuntimeError("click_gap 主键必须为 (pid, dt, pkg_name)")
|
|
nullable_required = {"pid", "dt", "pkg_name", "shareit_clicks", "af_clicks", "installs_ua", "clicks_diff", "updated_at"}
|
|
if any(by_name[name][3] != 1 for name in nullable_required):
|
|
raise RuntimeError("click_gap 必填列不得允许 NULL")
|
|
|
|
|
|
def read_existing_rows(path: str, start: str, end: str, pid: str = PID) -> list[dict[str, Any]]:
|
|
validate_existing_schema(path)
|
|
with sqlite3.connect(path) as conn:
|
|
conn.row_factory = sqlite3.Row
|
|
return [dict(row) for row in conn.execute("SELECT * FROM click_gap WHERE pid=? AND dt BETWEEN ? AND ?", (pid, start, end))]
|
|
|
|
|
|
def upsert_report(conn: sqlite3.Connection, rows: list[dict[str, Any]], start: str, end: str) -> int:
|
|
now = dt.datetime.now().astimezone().isoformat(timespec="seconds")
|
|
conn.execute("DELETE FROM click_gap WHERE pid=? AND dt BETWEEN ? AND ?", (PID, start, end))
|
|
values = []
|
|
for row in rows:
|
|
values.append((PID, row["dt"], row["attr_platform"], row["pkg_name"], row["shareit_clicks"], row["af_clicks"], row["installs_ua"], row["clicks_diff"], row["clicks_diff_rate"], now))
|
|
conn.executemany("INSERT INTO click_gap (pid,dt,attr_platform,pkg_name,shareit_clicks,af_clicks,installs_ua,clicks_diff,clicks_diff_rate,updated_at) VALUES (?,?,?,?,?,?,?,?,?,?)", values)
|
|
return len(values)
|
|
|
|
|
|
def superset_rows(start: str, end: str) -> list[dict[str, Any]]:
|
|
from superset_login import get_cookies
|
|
import requests
|
|
from requests_toolbelt import MultipartEncoder
|
|
session, csrf = get_cookies()
|
|
nextday = (dt.datetime.strptime(end, "%Y%m%d").date() + dt.timedelta(days=1)).strftime("%Y-%m-%d")
|
|
start_iso = dt.datetime.strptime(start, "%Y%m%d").strftime("%Y-%m-%d")
|
|
query = {"datasource": "114__table", "viz_type": "table", "slice_id": 1344, "url_params": {}, "time_range_endpoints": ["inclusive", "exclusive"], "granularity_sqla": "dt_as_time", "time_grain_sqla": "P1D", "time_range": f"{start_iso}T00:00:00 : {nextday}T00:00:00", "query_mode": "aggregate", "groupby": ["dt", "attr_platform", "pkg_name"], "metrics": ["clicks", "pb_install"], "all_columns": [], "array_join": [], "percent_metrics": [], "timeseries_limit_metric": ["dt_sort"], "order_by_cols": [], "row_limit": None, "order_desc": True, "adhoc_filters": [{"clause": "WHERE", "expressionType": "SIMPLE", "comparator": ["appsflyer"], "operator": "IN", "subject": "attr_platform"}, {"clause": "WHERE", "expressionType": "SIMPLE", "comparator": ["0"], "operator": "IN", "subject": "is_internal"}], "table_timestamp_format": "smart_date", "color_pn": True, "show_cell_bars": True}
|
|
encoder = MultipartEncoder(fields={"form_data": json.dumps(query)})
|
|
response = session.post('https://ads-bi.ushareit.org/superset/explore_json/?form_data={"slice_id":1344}&force=true', headers={"x-csrftoken": csrf, "content-type": encoder.content_type}, data=encoder, timeout=(10, 60))
|
|
if response.status_code != 200:
|
|
raise RuntimeError(f"Superset 请求失败: HTTP {response.status_code}")
|
|
payload = response.json()
|
|
data = payload.get("data") if isinstance(payload, dict) else None
|
|
if not isinstance(data, dict) or not isinstance(data.get("records"), list) or not isinstance(data.get("columns"), list):
|
|
raise RuntimeError("Superset 响应格式错误")
|
|
return [dict(zip(data["columns"], row)) if isinstance(row, (list, tuple)) else row for row in data["records"]]
|
|
|
|
|
|
def pkg_list(rows: list[dict[str, Any]]) -> list[str]:
|
|
totals: dict[str, float] = {}
|
|
for row in rows:
|
|
pkg = str(row.get("pkg_name") or "").strip()
|
|
if pkg:
|
|
totals[pkg] = totals.get(pkg, 0) + float(row.get("clicks") or 0)
|
|
return sorted(pkg for pkg, clicks in totals.items() if clicks > CLICK_NUM)
|
|
|
|
|
|
def appsflyer_rows(packages: list[str], start: str, end: str, browser: Any) -> list[dict[str, Any]]:
|
|
import requests
|
|
cookie = browser.get_cookie_str()
|
|
if not cookie:
|
|
raise RuntimeError("AppsFlyer cookie 为空")
|
|
payload = {"dates": {"start": dt.datetime.strptime(start, "%Y%m%d").strftime("%Y-%m-%d"), "end": dt.datetime.strptime(end, "%Y%m%d").strftime("%Y-%m-%d")}, "filters": {"app-id": []}, "view-type": "unified", "localization": {"timezone": "UTC", "currency": "USD"}, "groupings": [{"dimension": "date", "limit": 200}], "summations": ["totals", "others"], "metrics": [{"metric-id": "clicks"}, {"metric-id": "installs-ua"}], "format": "json", "granularity": "days", "implicit-sorting": True}
|
|
result: list[dict[str, Any]] = []
|
|
url = "https://hq1.appsflyer.com/platform/dashboard?widget=platform-table__performance:3"
|
|
for package in packages:
|
|
app_id = SPECIAL_PKGS.get(package, package)
|
|
payload["filters"]["app-id"] = [app_id]
|
|
last_error = None
|
|
for attempt in range(4):
|
|
try:
|
|
response = requests.post(url, data=json.dumps(payload), headers={"content-type": "application/json;charset=UTF-8", "cookie": cookie}, timeout=(10, 60))
|
|
if response.status_code == 429 or response.status_code >= 500:
|
|
raise RuntimeError(f"HTTP {response.status_code}")
|
|
if response.status_code != 200:
|
|
raise RuntimeError(f"HTTP {response.status_code}")
|
|
data = response.json().get("data")
|
|
if not isinstance(data, list) or any(not isinstance(item, dict) for item in data):
|
|
raise RuntimeError("响应格式错误")
|
|
for item in data:
|
|
item["app_id"] = package
|
|
result.extend(data)
|
|
break
|
|
except Exception as exc: # do not leak request contents
|
|
last_error = exc
|
|
if attempt < 3:
|
|
time.sleep(2 ** (attempt + 1))
|
|
else:
|
|
raise RuntimeError(f"AppsFlyer 查询失败 pkg={package}: {last_error}")
|
|
return result
|
|
|
|
|
|
def build_report(shareit: list[dict[str, Any]], af: list[dict[str, Any]], packages: list[str]) -> list[dict[str, Any]]:
|
|
shared: dict[tuple[str, str, str], float] = {}
|
|
for row in shareit:
|
|
if str(row.get("attr_platform") or "") != "appsflyer":
|
|
continue
|
|
pkg = str(row.get("pkg_name") or "").strip()
|
|
if not pkg or pkg not in packages:
|
|
continue
|
|
raw = str(row.get("dt") or "")[:10].replace("-", "")
|
|
date = date8(raw)
|
|
shared[(date, "appsflyer", pkg)] = shared.get((date, "appsflyer", pkg), 0) + float(row.get("clicks") or 0)
|
|
af_totals: dict[tuple[str, str], list[float]] = {}
|
|
for row in af:
|
|
raw = str(row.get("date") or "")[:10].replace("-", "")
|
|
date = date8(raw)
|
|
pkg = str(row.get("app_id") or "").strip()
|
|
key = (date, pkg)
|
|
values = af_totals.setdefault(key, [0.0, 0.0])
|
|
values[0] += float(row.get("filtersGranularityMetricIdClicksPeriod", row.get("clicks", 0)) or 0)
|
|
values[1] += float(row.get("attributionSourceAppsflyerFiltersGranularityMetricIdInstallsUaPeriod", row.get("installs_ua", 0)) or 0)
|
|
result = []
|
|
for (date, platform, pkg), share_clicks in shared.items():
|
|
af_clicks, installs = af_totals.get((date, pkg), [0.0, 0.0])
|
|
diff = share_clicks - af_clicks
|
|
result.append({"dt": date, "attr_platform": platform, "pkg_name": pkg, "shareit_clicks": finite_number(share_clicks, "shareit_clicks"), "af_clicks": finite_number(af_clicks, "af_clicks"), "installs_ua": finite_number(installs, "installs_ua"), "clicks_diff": finite_number(diff, "clicks_diff"), "clicks_diff_rate": None if share_clicks == 0 else finite_number(round(diff / share_clicks, 3), "clicks_diff_rate", True)})
|
|
result.sort(key=lambda row: (row["dt"], row["shareit_clicks"]), reverse=True)
|
|
if len({(r["dt"], r["pkg_name"]) for r in result}) != len(result):
|
|
raise RuntimeError("报告存在重复业务键")
|
|
return result
|
|
|
|
|
|
def validate_rows(rows: list[dict[str, Any]], start: str, end: str) -> None:
|
|
for row in rows:
|
|
if list(row) != REPORT_COLUMNS or date8(row["dt"]) < start or date8(row["dt"]) > end or not str(row["pkg_name"]).strip():
|
|
raise ValueError("报告字段、日期或包名不合法")
|
|
for field in REPORT_COLUMNS[3:]:
|
|
finite_number(row[field], field, field == "clicks_diff_rate")
|
|
|
|
|
|
def make_files(rows: list[dict[str, Any]], dates: list[str], out: Path) -> None:
|
|
out.mkdir(parents=True, exist_ok=True)
|
|
for date in dates:
|
|
content = [row for row in rows if row["dt"] == date]
|
|
target = out / f"{date}.json"
|
|
target.write_text(json.dumps(content, ensure_ascii=False, allow_nan=False, separators=(",", ":")) + "\n", encoding="utf-8")
|
|
index = {"schema_version": 1, "generated_at": dt.datetime.now().astimezone().isoformat(timespec="seconds"), "files": [{"date": date, "path": f"data/{date}.json"} for date in sorted(dates, reverse=True)]}
|
|
(out / "index.json").write_text(json.dumps(index, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
|
|
|
|
|
|
def sensitive_check(paths: list[Path]) -> None:
|
|
pattern = re.compile(r"cookie|authorization|password|api[_-]?key|token", re.I)
|
|
for path in paths:
|
|
if path.name.startswith(".env") or path.suffix in {".db", ".log"}:
|
|
raise RuntimeError(f"禁止发布敏感文件: {path.name}")
|
|
if path.suffix in {".json", ".html", ".md"} and pattern.search(path.read_text(encoding="utf-8")):
|
|
raise RuntimeError(f"文件疑似包含敏感字段: {path.name}")
|
|
|
|
|
|
def publish_files(repo: Path, generated: Path, dates: list[str]) -> None:
|
|
data = repo / "data"
|
|
data.mkdir(exist_ok=True)
|
|
for date in dates:
|
|
source = generated / f"{date}.json"
|
|
tmp = data / f".{date}.tmp"
|
|
shutil.copyfile(source, tmp)
|
|
os.replace(tmp, data / f"{date}.json")
|
|
os.replace(generated / "index.json", data / "index.json")
|
|
|
|
|
|
def git_run(repo: Path, args: list[str]) -> subprocess.CompletedProcess[str]:
|
|
return subprocess.run(["git", *args], cwd=repo, text=True, capture_output=True, timeout=120, check=False)
|
|
|
|
|
|
def git_publish(repo: Path, start: str, end: str, no_push: bool) -> str:
|
|
if not (repo / ".git").exists():
|
|
raise RuntimeError("仓库尚未初始化；请先执行 git init 并配置 remote")
|
|
status = git_run(repo, ["status", "--porcelain"]).stdout.strip().splitlines()
|
|
allowed = {"README.md", ".gitignore", "index.html", "scripts/af_click_gap_pipeline.py", "launchd/com.roasbloom.af-click-gap.plist.template"}
|
|
allowed.update({f"data/{date}.json" for date in (repo / "data").glob("*.json")})
|
|
unexpected = [line for line in status if line[3:] not in allowed]
|
|
if unexpected:
|
|
raise RuntimeError("工作区已有未预期改动: " + ", ".join(unexpected))
|
|
paths = ["README.md", ".gitignore", "index.html", "scripts/af_click_gap_pipeline.py", "launchd/com.roasbloom.af-click-gap.plist.template", "data"]
|
|
add = git_run(repo, ["add", *paths])
|
|
if add.returncode:
|
|
raise RuntimeError("git add 失败: " + add.stderr.strip())
|
|
staged = git_run(repo, ["diff", "--cached", "--name-only"])
|
|
if staged.returncode or not staged.stdout.strip():
|
|
raise RuntimeError("没有可提交的文件")
|
|
commit = git_run(repo, ["commit", "-m", f"feat: publish click gap {start}-{end}"])
|
|
if commit.returncode:
|
|
raise RuntimeError("git commit 失败: " + commit.stderr.strip())
|
|
commit_hash = git_run(repo, ["rev-parse", "HEAD"]).stdout.strip()
|
|
if no_push:
|
|
return commit_hash + " (未 push)"
|
|
remote = git_run(repo, ["remote", "-v"])
|
|
if remote.returncode or not remote.stdout.strip():
|
|
raise RuntimeError("未配置 Git remote；本地 commit 已保留")
|
|
push = git_run(repo, ["push"])
|
|
if push.returncode:
|
|
raise RuntimeError("git push 失败（本地 commit 已保留）: " + push.stderr.strip())
|
|
return commit_hash + " (已 push)"
|
|
|
|
|
|
def parse_args() -> argparse.Namespace:
|
|
parser = argparse.ArgumentParser(description="Extract and publish AppsFlyer click-gap JSON")
|
|
parser.add_argument("--start-date", help="补数开始日期 YYYY-MM-DD")
|
|
parser.add_argument("--end-date", help="补数结束日期 YYYY-MM-DD")
|
|
parser.add_argument("--dry-run", action="store_true", help="只提取并校验，不写正式文件、数据库或 Git")
|
|
group = parser.add_mutually_exclusive_group()
|
|
group.add_argument("--no-push", action="store_true", help="写文件和数据库但不 push")
|
|
group.add_argument("--push", action="store_true", help="写文件、数据库并 commit/push（默认）")
|
|
parser.add_argument("--db-path", default=DB_PATH, help=argparse.SUPPRESS)
|
|
return parser.parse_args()
|
|
|
|
|
|
def main() -> int:
|
|
args = parse_args()
|
|
try:
|
|
if args.dry_run and (args.no_push or args.push):
|
|
raise ValueError("--dry-run 不可与 --push/--no-push 同时使用")
|
|
start, end = window(args.start_date, args.end_date)
|
|
validate_existing_schema(args.db_path)
|
|
shareit = superset_rows(start, end)
|
|
packages = pkg_list(shareit)
|
|
af: list[dict[str, Any]] = []
|
|
browser = None
|
|
if packages:
|
|
from af_browser import AFBrowser
|
|
browser = AFBrowser()
|
|
try:
|
|
af = appsflyer_rows(packages, start, end, browser)
|
|
finally:
|
|
try:
|
|
browser.close()
|
|
except Exception:
|
|
LOG.warning("关闭浏览器失败")
|
|
rows = build_report(shareit, af, packages)
|
|
validate_rows(rows, start, end)
|
|
dates = [(dt.datetime.strptime(start, "%Y%m%d").date() + dt.timedelta(days=i)).strftime("%Y%m%d") for i in range((dt.datetime.strptime(end, "%Y%m%d").date() - dt.datetime.strptime(start, "%Y%m%d").date()).days + 1)]
|
|
repo = Path(__file__).resolve().parents[1]
|
|
with tempfile.TemporaryDirectory(prefix="af-click-gap-") as temp:
|
|
generated = Path(temp) / "data"
|
|
make_files(rows, dates, generated)
|
|
sensitive_check(list(generated.glob("*")))
|
|
if args.dry_run:
|
|
LOG.info("dry-run 成功: %s-%s, %d 行", start, end, len(rows))
|
|
return 0
|
|
publish_files(repo, generated, dates)
|
|
with sqlite3.connect(args.db_path) as conn:
|
|
conn.execute("BEGIN")
|
|
upsert_report(conn, rows, start, end)
|
|
conn.commit()
|
|
if args.no_push:
|
|
LOG.info("已发布本地文件和 SQLite，未执行 Git")
|
|
else:
|
|
result = git_publish(repo, start, end, False)
|
|
LOG.info("Git 结果: %s", result)
|
|
return 0
|
|
except ValueError as exc:
|
|
LOG.error("输入失败: %s", exc)
|
|
return 2
|
|
except Exception as exc:
|
|
LOG.error("任务失败: %s", exc)
|
|
return 1
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|