python实现豆瓣电影搜索并自动添加相关信息

1.豆瓣电影搜索

2.豆瓣电影信息自动添加

搜索

众所周知，豆瓣搜索有加密，得解密才行，还好网上众多大神都给破解了，那咱们拿来直接使用就行

相关代码仓库：xadmin-server/movies/utils/douban/search.py at movies · nineaiyu/xadmin-server (github.com)

核心搜索并解密代码如下

import base64
import datetime
import plistlib
import re
import struct
from plistlib import FMT_BINARY, _BinaryPlistParser, _undefinedimport requests
import xxhash
from Cryptodome.Cipher import ARC4
from math import floordef _read_object(self, ref):"""read the object by reference.May recursively read sub-objects (content of an array/dict/set)"""result = self._objects[ref]if result is not _undefined:return resultoffset = self._object_offsets[ref]self._fp.seek(offset)token = self._fp.read(1)[0]tokenH, tokenL = token & 0xF0, token & 0x0Fif token == 0x00:result = Noneelif token == 0x08:result = Falseelif token == 0x09:result = True# The referenced source code also mentions URL (0x0c, 0x0d) and# UUID (0x0e), but neither can be generated using the Cocoa libraries.elif token == 0x0f:result = b''elif tokenH == 0x10:  # intresult = int.from_bytes(self._fp.read(1 << tokenL),'big', signed=tokenL >= 3)elif token == 0x22:  # realresult = struct.unpack('>f', self._fp.read(4))[0]elif token == 0x23:  # realresult = struct.unpack('>d', self._fp.read(8))[0]elif token == 0x33:  # datef = struct.unpack('>d', self._fp.read(8))[0]# timestamp 0 of binary plists corresponds to 1/1/2001# (year of Mac OS X 10.0), instead of 1/1/1970.result = (datetime.datetime(2001, 1, 1) +datetime.timedelta(seconds=f))elif tokenH == 0x40:  # datas = self._get_size(tokenL)result = self._fp.read(s)if len(result) != s:raise plistlib.InvalidFileException()elif tokenH == 0x60:  # ascii strings = self._get_size(tokenL)data = self._fp.read(s)if len(data) != s:raise plistlib.InvalidFileException()result = data.decode('ascii')elif tokenH == 0x50:  # unicode strings = self._get_size(tokenL) * 2data = self._fp.read(s)if len(data) != s:raise plistlib.InvalidFileException()result = data.decode('utf-16be')elif tokenH == 0x80:  # UID# used by Key-Archiver plist filesresult = plistlib.UID(int.from_bytes(self._fp.read(1 + tokenL), 'big'))elif tokenH == 0xA0:  # arrays = self._get_size(tokenL)obj_refs = self._read_refs(s)result = []self._objects[ref] = resultresult.extend(self._read_object(x) for x in obj_refs)# tokenH == 0xB0 is documented as 'ordset', but is not actually# implemented in the Apple reference code.# tokenH == 0xC0 is documented as 'set', but sets cannot be used in# plists.elif tokenH == 0xD0:  # dicts = self._get_size(tokenL)key_refs = self._read_refs(s)obj_refs = self._read_refs(s)result = self._dict_type()self._objects[ref] = resulttry:for k, o in zip(key_refs, obj_refs):result[self._read_object(k)] = self._read_object(o)except TypeError:raise plistlib.InvalidFileException()else:raise plistlib.InvalidFileException()self._objects[ref] = resultreturn result_BinaryPlistParser._read_object = _read_objectdef crypto_rc4(raw_data: bytes, sec_key: str):cipher = ARC4.new(sec_key.encode())rc4_bytes = cipher.encrypt(raw_data)return rc4_bytesdef search_from_douban(key):url = f'https://search.douban.com/movie/subject_search?search_text={key}&cat=1002'headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 Edg/120.0.0.0',}res = requests.get(url, headers=headers)print(f"search douban url: {res.status_code} {res.content}")data = re.search(r'window.__DATA__ = "(.+?)"', res.text, flags=re.DOTALL).group(1)# print(data)i = 16a = base64.b64decode(data)s = floor((len(a) - 2 * i) / 3)u = a[s: s + i]raw_bytes = a[0:s] + a[s + i:]# print(u)sec_key = xxhash.xxh64_hexdigest(u, 41405)# print(sec_key)rc4_bytes = crypto_rc4(raw_bytes, sec_key)# print(rc4_bytes)pb_results = plistlib.loads(rc4_bytes, fmt=FMT_BINARY)results = []# print("最终结果为：")# print(pb_results)for x in pb_results:# print(1111, type(x), x)try:data = x.get(b'k')info = {'title': '', 'info': '', 'actor': '', 'url': ''}for s in data:if isinstance(s, list) and len(s) > 0 and s[0].get('title'):# results = []for x in s:results.append({'title': x['title'].replace('\u200e', '').strip(),'info': x.get('abstract'),'actor': x.get('abstract_2'), 'url': x.get('url')})# return resultsif isinstance(s, str):if 's_ratio_poster' in s and s.startswith('https://img'):info['s_ratio_poster'] = selif '\u200e' in s:info['title'] = s.replace('\u200e', '').strip()elif s.startswith('https://movie.douban.com'):info['url'] = selif ' / ' in s:if s.endswith('分钟'):info['info'] = selse:info['actor'] = sif info and info['title'] and info['url']:results.insert(0, dict(info.items()))except Exception as e:passreturn resultsif __name__ == '__main__':print(search_from_douban('流浪地球'))