LivereExport

download.py

import datetime
import json
import math

import requests

COOKIES = """name=value"""

session = requests.Session()
for cookie in COOKIES.split(";"):
  key, value = cookie.split("=", 1)
  session.cookies.set(key, value)

results = []

page = 1
count = 10

while math.ceil(count / 10) >= page:
  response = session.post("https://livere.com/insight/managereply/period", {
    "startDate": "2017-01-01",
    "endDate": datetime.date.today(),
    "sort": "regdate",
    "order": "desc",
    "pageNum": page,
  })
  response_json = response.json()
  results += response_json["resultData"]
  count = response_json["count"]
  page += 1

with open("result.json", "w", -1, "utf8", newline="\n") as writer:
  json.dump(results, writer, ensure_ascii=False, indent=2)

split.py

import json
import os
import re
import urllib.parse
from datetime import datetime, timedelta, timezone

with open("result.json", "r", -1, "utf8") as reader:
  results: list[dict] = json.load(reader)[::-1]

url_data: dict[str, dict[str, list[str]]] = {}

for result in results:
  url = result["site"]
  content: str = result["content"]
  reply_seq = result["reply_seq"]
  parent_seq = result["parent_seq"]
  author: str = result["name"].strip()
  date: datetime = (
    datetime.strptime(result["regdate"].strip(), "%Y-%m-%d-%I:%M:%S %p")
    .replace(tzinfo=timezone(timedelta(hours=9)))
    .astimezone(timezone(timedelta(hours=8)))
  )
  images = []
  i = 1
  while f"image{i}" in result:
    images.append(result[f"image{i}"])
    i += 1

  content = re.sub(r"\n\n\n+", "\n\n", content).replace("\n", "  \n").replace("  \n  \n", "\n\n")

  path = urllib.parse.unquote(url.split("/", 3)[-1].split("?")[0].split("#")[0], encoding="utf8")

  if path.endswith("/"):
    path += "index.html"
  assert path.endswith(".html")
  path = path.removesuffix(".html")
  if path not in url_data:
    url_data[path] = {}
  if parent_seq not in url_data[path]:
    url_data[path][parent_seq] = []

  output_str = [
    f"*****{author} {'评论于' if reply_seq == parent_seq else '回复于'} {datetime.strftime(date, '%Y-%m-%d %H:%M:%S')} (UTC+8)*****\n\n{content}"
  ]
  for image in images:
    output_str.append(f"\n\n![{image}]({image})")
  url_data[path][parent_seq].append("".join(output_str))

for path, comments in url_data.items():
  os.makedirs(os.path.join("output", path), exist_ok=True)
  for id, content in sorted(comments.items(), key=lambda x: int(x[0])):
    with open(os.path.join("output", path, f"{id}.md"), "w", -1, "utf8") as writer:
      writer.write(f"> 评论导出自来必力\n\n")
      writer.write("\n\n".join(content))