# coding = utf-8 # !/usr/bin/python """ 作者 丢丢推荐 🚓 内容均从互联网收集而来 仅供交流学习使用 版权归原创者所有 如侵犯了您的权益 请通知作者 将及时删除侵权内容 ====================diudiu==================== """ import requests from bs4 import BeautifulSoup import re from base.spider import Spider import sys import json import base64 import urllib.parse sys.path.append('..') xurl = "http://www.45b7.com" headerx = { 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.87 Safari/537.36' } pm = '' class Spider(Spider): global xurl global headerx def getName(self): return "首页" def init(self, extend): pass def isVideoFormat(self, url): pass def manualVideoCheck(self): pass def extract_middle_text(self, text, start_str, end_str, pl, start_index1: str = '', end_index2: str = ''): if pl == 3: plx = [] while True: start_index = text.find(start_str) if start_index == -1: break end_index = text.find(end_str, start_index + len(start_str)) if end_index == -1: break middle_text = text[start_index + len(start_str):end_index] plx.append(middle_text) text = text.replace(start_str + middle_text + end_str, '') if len(plx) > 0: purl = '' for i in range(len(plx)): matches = re.findall(start_index1, plx[i]) output = "" for match in matches: match3 = re.search(r'(?:^|[^0-9])(\d+)(?:[^0-9]|$)', match[1]) if match3: number = match3.group(1) else: number = 0 if 'http' not in match[0]: output += f"#{'📽️集多👉' + match[1]}${number}{xurl}{match[0]}" else: output += f"#{'📽️集多👉' + match[1]}${number}{match[0]}" output = output[1:] purl = purl + output + "$$$" purl = purl[:-3] return purl else: return "" else: start_index = text.find(start_str) if start_index == -1: return "" end_index = text.find(end_str, start_index + len(start_str)) if end_index == -1: return "" if pl == 0: middle_text = text[start_index + len(start_str):end_index] return middle_text.replace("\\", "") if pl == 1: middle_text = text[start_index + len(start_str):end_index] matches = re.findall(start_index1, middle_text) if matches: jg = ' '.join(matches) return jg if pl == 2: middle_text = text[start_index + len(start_str):end_index] matches = re.findall(start_index1, middle_text) if matches: new_list = [f'✨集多👉{item}' for item in matches] jg = '$$$'.join(new_list) return jg def homeContent(self, filter): result = {} result = {"class": [{"type_id": "51", "type_name": "有声动漫🌠"}, {"type_id": "52", "type_name": "女频恋爱🌠"}, {"type_id": "53", "type_name": "反转爽剧🌠"}, {"type_id": "54", "type_name": "古装仙侠🌠"}, {"type_id": "55", "type_name": "年代穿越🌠"}, {"type_id": "56", "type_name": "脑洞悬疑🌠"}, {"type_id": "57", "type_name": "现代都市🌠"}], "list": [], "filters": {"51": [{"key": "年代", "name": "年代", "value": [{"n": "全部", "v": ""}, {"n": "2024", "v": "2024"}, {"n": "2023", "v": "2023"}, {"n": "2022", "v": "2022"}, {"n": "2021", "v": "2021"}, {"n": "2020", "v": "2020"}, {"n": "2019", "v": "2019"}, {"n": "2018", "v": "2018"}]}], "52": [{"key": "年代", "name": "年代", "value": [{"n": "全部", "v": ""}, {"n": "2024", "v": "2024"}, {"n": "2023", "v": "2023"}, {"n": "2022", "v": "2022"}, {"n": "2021", "v": "2021"}, {"n": "2020", "v": "2020"}, {"n": "2019", "v": "2019"}, {"n": "2018", "v": "2018"}]}], "53": [{"key": "年代", "name": "年代", "value": [{"n": "全部", "v": ""}, {"n": "2024", "v": "2024"}, {"n": "2023", "v": "2023"}, {"n": "2022", "v": "2022"}, {"n": "2021", "v": "2021"}, {"n": "2020", "v": "2020"}, {"n": "2019", "v": "2019"}, {"n": "2018", "v": "2018"}]}], "54": [{"key": "年代", "name": "年代", "value": [{"n": "全部", "v": ""}, {"n": "2024", "v": "2024"}, {"n": "2023", "v": "2023"}, {"n": "2022", "v": "2022"}, {"n": "2021", "v": "2021"}, {"n": "2020", "v": "2020"}, {"n": "2019", "v": "2019"}, {"n": "2018", "v": "2018"}]}], "55": [{"key": "年代", "name": "年代", "value": [{"n": "全部", "v": ""}, {"n": "2024", "v": "2024"}, {"n": "2023", "v": "2023"}, {"n": "2022", "v": "2022"}, {"n": "2021", "v": "2021"}, {"n": "2020", "v": "2020"}, {"n": "2019", "v": "2019"}, {"n": "2018", "v": "2018"}]}], "56": [{"key": "年代", "name": "年代", "value": [{"n": "全部", "v": ""}, {"n": "2024", "v": "2024"}, {"n": "2023", "v": "2023"}, {"n": "2022", "v": "2022"}, {"n": "2021", "v": "2021"}, {"n": "2020", "v": "2020"}, {"n": "2019", "v": "2019"}, {"n": "2018", "v": "2018"}]}], "57": [{"key": "年代", "name": "年代", "value": [{"n": "全部", "v": ""}, {"n": "2024", "v": "2024"}, {"n": "2023", "v": "2023"}, {"n": "2022", "v": "2022"}, {"n": "2021", "v": "2021"}, {"n": "2020", "v": "2020"}, {"n": "2019", "v": "2019"}, {"n": "2018", "v": "2018"}]}]}} return result def homeVideoContent(self): videos = [] try: detail = requests.get(url=xurl + "/vodtype/49.html", headers=headerx) detail.encoding = "utf-8" res = detail.text doc = BeautifulSoup(res, "lxml") soups = doc.find_all('div', class_="module-poster-items-base") for soup in soups: vods = soup.find_all('a') for vod in vods: name = vod.find('img')['alt'] id = vod['href'] pic = vod.find('img')['data-original'] if 'http' not in pic: pic = xurl + pic remarks = vod.find('div', class_="module-item-note") remark = remarks.text.strip() video = { "vod_id": id, "vod_name": name, "vod_pic": pic, "vod_remarks": '集多推荐📽️' + remark } videos.append(video) result = {'list': videos} return result except: pass def categoryContent(self, cid, pg, filter, ext): result = {} videos = [] if pg: page = int(pg) else: page = 1 if '年代' in ext.keys(): NdType = ext['年代'] else: NdType = '' if page == 1: url = f'{xurl}/vodshow/{cid}-----------.html' else: url = f'{xurl}/vodshow/{cid}--------{str(page)}---{NdType}.html' try: detail = requests.get(url=url, headers=headerx) detail.encoding = "utf-8" res = detail.text doc = BeautifulSoup(res, "lxml") soups = doc.find_all('div', class_="module-poster-items-base") for soup in soups: vods = soup.find_all('a') for vod in vods: name = vod.find('img')['alt'] id = vod['href'] pic = vod.find('img')['data-original'] if 'http' not in pic: pic = xurl + pic remarks = vod.find('div', class_="module-item-note") remark = remarks.text.strip() video = { "vod_id": id, "vod_name": name, "vod_pic": pic, "vod_remarks": '集多推荐📽️' + remark } videos.append(video) except: pass result = {'list': videos} result['page'] = pg result['pagecount'] = 9999 result['limit'] = 90 result['total'] = 999999 return result def detailContent(self, ids): global pm did = ids[0] result = {} videos = [] playurl = '' if 'http' not in did: did = xurl + did res1 = requests.get(url=did, headers=headerx) res1.encoding = "utf-8" res = res1.text url = 'https://fs-im-kefu.7moor-fs1.com/ly/4d2c3f00-7d4c-11e5-af15-41bf63ae4ea0/1732707176882/jiduo.txt' response = requests.get(url) response.encoding = 'utf-8' code = response.text name = self.extract_middle_text(code, "s1='", "'", 0) Jumps = self.extract_middle_text(code, "s2='", "'", 0) content = '集多🎉为您介绍剧情📢本资源来源于网络🚓侵权请联系删除👉' + self.extract_middle_text(res,'