devplacepy/copy.py at 499f91e16a6d908b2c7545a32147ac255f31ebcd

 # retoor <retoor@molodetz.nl>
 from __future__ import annotations
 import re
 from devplacepy.services.jobs.isslop.analysis.domsignals.base import DomPageContext, dom_check
 from devplacepy.services.jobs.isslop.analysis.signals import (
     AXIS_ORIGIN,
     SEVERITY_MEDIUM,
     SEVERITY_WEAK,
     Signal,
 )
 CLICHE_PHRASES: tuple[str, ...] = (
     r"unlock (the )?(power|potential) of",
     r"unleash the power of",
     r"take your .{1,40} to the next level",
     r"elevate your",
     r"seamlessly integrat(e|es|ion)",
     r"revolutioniz(e|ing) the way",
     r"whether you('re| are) a .{1,30} or (a )?.{1,30}",
     r"delve into",
     r"dive into the world of",
     r"embark on a journey",
     r"push(ing)? the boundaries of",
     r"at the forefront of",
     r"game[- ]chang(er|ing)",
     r"pave the way for",
     r"bridging the gap between",
     r"navigate the complexities of",
     r"foster a culture of",
     r"harness the power of",
     r"cutting[- ]edge",
     r"future[- ]proof",
     r"world[- ]class",
     r"enterprise[- ]grade",
     r"streamline(d)?",
     r"empower(ing)?",
     r"supercharg(e|ed|ing)",
 )
 CLICHE_PATTERN = re.compile("|".join(CLICHE_PHRASES), re.IGNORECASE)
 BUZZWORDS: tuple[str, ...] = ("delve", "crucial", "intricate", "nuanced", "myriad", "realm", "tapestry", "landscape")
 BUZZWORD_THRESHOLD: int = 3
 BUZZWORD_PATTERNS: tuple[re.Pattern[str], ...] = tuple(
     re.compile(rf"\b{word}\b", re.IGNORECASE) for word in BUZZWORDS
 )
 HEADING_EMOJI_PATTERN = re.compile(r"[\U0001F300-\U0001FAFF✅⭐✨\U0001F680]")
 FAQ_PATTERNS: tuple[re.Pattern[str], ...] = (
     re.compile(r"^what is\b", re.IGNORECASE),
     re.compile(r"^how does .{1,30} work\??$", re.IGNORECASE),
     re.compile(r"^is (it|.{1,20}) secure\??$", re.IGNORECASE),
     re.compile(r"^can i cancel", re.IGNORECASE),
     re.compile(r"^do you offer a? ?(free trial|refund)", re.IGNORECASE),
 )
 FAQ_PATTERN_THRESHOLD: int = 3
 def _heading_texts(page: DomPageContext) -> list[str]:
     return [
         str(heading.get("text", ""))
         for heading in (page.dom.get("headings") or [])
         if isinstance(heading, dict) and heading.get("text")
     ]
 def _text_blob(page: DomPageContext) -> str:
     parts = list(_heading_texts(page))
     for image in page.dom.get("images", []) or []:
         if isinstance(image, dict) and image.get("alt"):
             parts.append(str(image["alt"]))
     meta = page.dom.get("meta", {}) or {}
     description = meta.get("description") if isinstance(meta, dict) else ""
     if description:
         parts.append(str(description))
     return "\n".join(parts)
 def _detect_template_copy(blob: str) -> Signal | None:
     match = CLICHE_PATTERN.search(blob)
     if not match:
         return None
     return Signal(
         "TEMPLATE_COPY_DOM",
         "Stock AI landing-page cliche phrase in rendered copy",
         SEVERITY_MEDIUM,
         AXIS_ORIGIN,
 .5,
 ,
         match.group(0)[:150],
     )
 def _detect_buzzword_cluster(blob: str) -> Signal | None:
     hits = [pattern.pattern for pattern in BUZZWORD_PATTERNS if pattern.search(blob)]
     if len(hits) < BUZZWORD_THRESHOLD:
         return None
     return Signal(
         "AI_BUZZWORD_CLUSTER",
         f"Elevated buzzword cluster ({len(hits)} distinct terms)",
         SEVERITY_WEAK,
         AXIS_ORIGIN,
 .0,
 ,
         ", ".join(hits),
     )
 def _detect_emoji_heading(page: DomPageContext) -> Signal | None:
     for text in _heading_texts(page):
         if HEADING_EMOJI_PATTERN.search(text):
             return Signal(
                 "EMOJI_HEADING_DOM",
                 "Emoji embedded inside a rendered heading",
                 SEVERITY_MEDIUM,
                 AXIS_ORIGIN,
 .0,
 ,
                 text[:100],
             )
     return None
 def _detect_generic_faq_template(page: DomPageContext) -> Signal | None:
     texts = _heading_texts(page)
     matched = 0
     for pattern in FAQ_PATTERNS:
         if any(pattern.search(text.strip()) for text in texts):
             matched += 1
     if matched < FAQ_PATTERN_THRESHOLD:
         return None
     return Signal(
         "GENERIC_FAQ_TEMPLATE",
         f"Generic templated FAQ question set ({matched} canonical patterns matched)",
         SEVERITY_MEDIUM,
         AXIS_ORIGIN,
 .5,
 ,
         f"{matched} FAQ patterns matched",
     )
 @dom_check
 def detect_copy_signals(page: DomPageContext) -> list[Signal]:
     blob = _text_blob(page)
     findings: list[Signal] = []
     for signal in (
         _detect_template_copy(blob),
         _detect_buzzword_cluster(blob),
         _detect_emoji_heading(page),
         _detect_generic_faq_template(page),
     ):
         if signal is not None:
             findings.append(signal)
     return findings