def cli():
p = argparse.ArgumentParser()
p.add_argument("blogpath", help="directory of Markdown posts to analyze")
p.add_argument("xlsfile", help="path of .xlsx file to write")
p.add_argument("--only", help="part of page to analyze", choices=["title", "description"])
p.add_argument("-ext", help="filename suffix", default=".md")
P = p.parse_args()
blog_path = Path(P.blogpath).expanduser()
xlsx = Path(P.xlsfile).expanduser()
xlsx.parent.mkdir(parents=True, exist_ok=True)
if blog_path.is_file():
files = [blog_path]
elif blog_path.is_dir():
files = list(blog_path.rglob(f"*{P.ext}"))
else:
raise NotADirectoryError(blog_path)
cols = ["pos", "neu", "neg", "compound"]
if P.only:
cols.append(P.only)
dat = pandas.DataFrame(index=[f.stem for f in files], columns=cols)
now = datetime.datetime.now()
for i, file in enumerate(files):
print(f"{i+1} / {len(files)} {file.stem:<80}", end="\r")
header = hugoutils.get_header(file)[0]
if header is not None and "expiryDate" in header:
if datetime.datetime.strptime(header["expiryDate"][:10], "%Y-%m-%d") < now:
print("skip", file)
continue
if P.only:
try:
text = header[P.only]
except TypeError:
continue
except KeyError:
logging.error(f"{file.stem} does not have {P.only}")
continue
else:
text = file.read_text(errors="ignore")
s = analyze_post(text)
if P.only:
dat.loc[file.stem] = [s["pos"], s["neu"], s["neg"], s["compound"], text]
else:
dat.loc[file.stem] = [s["pos"], s["neu"], s["neg"], s["compound"]]
if blog_path.is_file():
print(dat)
else:
dat.to_excel(xlsx)
def get_tags(path: Path, taxonomy_type: str) -> set[str]:
files = list(path.glob("*.md"))
dat: set[str] = set()
for f in files:
header = hugoutils.get_header(f)[0]
try:
tags = header[taxonomy_type]
except (TypeError, KeyError):
continue
for tag in tags:
dat.add(tag)
return dat
p.add_argument("path", help="path to read Markdown blog files")
p.add_argument("xlsx", help="excel filename to write")
p.add_argument("-ext", help="filename suffix", default=".md")
p = p.parse_args()
inpath = Path(p.path).expanduser()
if not inpath.is_dir():
raise NotADirectoryError(inpath)
xlsx = Path(p.xlsx).expanduser()
files = list(inpath.rglob(f"*{p.ext}"))
dat: dict[str, int] = {}
for f in files:
header = hugoutils.get_header(f)[0]
try:
tags = header["tags"]
except (TypeError, KeyError):
continue
except Exception as e:
logging.error(f"{e}: {f.stem}")
for tag in tags:
try:
dat[tag] += 1
except KeyError:
dat[tag] = 1
pandas.DataFrame(index=dat.keys(), data=dat.values(),
columns=["count"]).to_excel(xlsx)