import csv,datetime,hashlib,json,pathlib,sys
manifest,target=map(pathlib.Path,sys.argv[1:3])
entries=json.loads(manifest.read_text(encoding="utf-8"))
if not isinstance(entries,list) or len(entries)!=2:raise ValueError("Exactly one organic and one all-traffic saved request required")
scopes={};base=None;request_ids=set()
for entry in entries:
if entry.get("action")!="xiaohongshu.pgy.get_blogger_notes":raise ValueError("Use note cases, not aggregate metrics")
params=entry["params"]
allowed={"user_id","note_type","order_type","advertise_switch","page_number","page_size","feature_tag","content_tag","is_third_platform"}
if not isinstance(params,dict) or set(params)-allowed:raise ValueError("Use only documented input fields")
for tag in ("feature_tag","content_tag"):
if tag in params and (not isinstance(params[tag],str) or len(params[tag])>64):raise ValueError("Invalid tag filter")
if "is_third_platform" in params and (type(params["is_third_platform"]) is not int or params["is_third_platform"] not in (0,1)):raise ValueError("Invalid cross-platform filter")
scope=params.get("advertise_switch")
if type(scope) is not int or scope not in (0,1) or scope in scopes:raise ValueError("Need distinct scopes 0 and 1")
if not isinstance(params.get("user_id"),str) or not params["user_id"].strip():raise ValueError("Record user_id")
if params.get("order_type")!=1 or type(params.get("order_type")) is not int:raise ValueError("Use newest order, not scope-dependent reading rank")
for key in ("page_number","page_size","note_type"):
if type(params.get(key)) is not int:raise ValueError("Record explicit note/page settings")
if not 1<=params["page_number"]<=1000 or not 1<=params["page_size"]<=8 or params["note_type"] not in (1,2,3,4):raise ValueError("Invalid note/page settings")
other={key:value for key,value in params.items() if key!="advertise_switch"}
if base is None:base=other
if base!=other:raise ValueError("Only traffic scope may differ")
stamp=entry["collected_at"];dt=datetime.datetime.fromisoformat(stamp.replace("Z","+00:00"))
if dt.tzinfo is None:raise ValueError("Timezone required")
path=pathlib.Path(entry["response_file"])
if not path.is_absolute():path=manifest.parent/path
raw=path.read_bytes();digest=hashlib.sha256(raw).hexdigest()
r=json.loads(raw)
if r.get("error") is not None or r.get("status")!="succeeded" or r.get("action")!=entry["action"]:raise ValueError("Failed or wrong response")
rid=r.get("request_id")
if not isinstance(rid,str) or not rid.strip() or rid in request_ids:raise ValueError("Distinct request IDs required")
request_ids.add(rid)
envelope=r.get("data")
if not isinstance(envelope,dict) or envelope.get("success") is not True:raise ValueError("PGY business failure")
data=envelope.get("data")
if not isinstance(data,dict) or not isinstance(data.get("list"),list):raise ValueError("Expected non-null note list")
notes={}
for item in data["list"]:
if not isinstance(item,dict):raise ValueError("Bad note object")
note=item.get("noteId")
if not isinstance(note,str) or not note.strip() or note in notes:raise ValueError("Distinct real noteId required per page")
value=item.get("readNum")
if type(value) is int and value>2**53-1:raise ValueError("Unsafe JSON count; preserve an original digit string instead")
if isinstance(value,str) and value.isascii() and value.isdigit():value=int(value)
if value is not None and (type(value) is not int or value<0):raise ValueError("readNum must be integer/digit string or missing")
notes[note]=value
scopes[scope]={"notes":notes,"request_id":rid,"collected_at":stamp,"source_file":str(path.resolve()),"sha256":digest}
rows=[]
for note in sorted(set(scopes[0]["notes"])|set(scopes[1]["notes"])):
organic=scopes[0]["notes"].get(note);all_reads=scopes[1]["notes"].get(note)
present0=note in scopes[0]["notes"];present1=note in scopes[1]["notes"]
state="both" if present0 and present1 else ("organic_only" if present0 else "all_only")
delta=all_reads-organic if organic is not None and all_reads is not None else None
rows.append({"noteId":note,"coverage":state,"organic_reads":organic,"all_reads":all_reads,"observed_difference":delta,
"review":"missing_metric" if state=="both" and delta is None else ("negative_difference" if delta is not None and delta<0 else ""),
"organic_request_id":scopes[0]["request_id"],"all_request_id":scopes[1]["request_id"],
"organic_collected_at":scopes[0]["collected_at"],"all_collected_at":scopes[1]["collected_at"],
"organic_source_sha256":scopes[0]["sha256"],"all_source_sha256":scopes[1]["sha256"]})
def cell(value):
if value is None:return ""
if isinstance(value,int):return value
return "'"+value if value.lstrip().startswith(("=","+","-","@")) or value.startswith(("\t","\r","\n")) else value
with target.open("x",encoding="utf-8-sig",newline="") as output:
writer=csv.DictWriter(output,fieldnames=["noteId","coverage","organic_reads","all_reads","observed_difference","review","organic_request_id","all_request_id","organic_collected_at","all_collected_at","organic_source_sha256","all_source_sha256"])
writer.writeheader();writer.writerows({key:cell(value) for key,value in row.items()} for row in rows)
print(str(target))