import os import re import traceback import uuid from typing import Union from urllib.parse import urljoin import aiohttp import ujson as json from bs4 import BeautifulSoup, Comment from config import Config from core.logger import Logger web_render = Config('web_render') async def get_infobox_pic(link, page_link, headers, section=None) -> Union[str, bool]: if not web_render: return False try: Logger.info('Starting find infobox/section..') if link[-1] != '/': link += '/' try: async with aiohttp.ClientSession(headers=headers) as session: async with session.get(page_link, timeout=aiohttp.ClientTimeout(total=20)) as req: html = await req.read() except: traceback.print_exc() return False soup = BeautifulSoup(html, 'html.parser') pagename = uuid.uuid4() url = os.path.abspath(f'./cache/{pagename}.html') if os.path.exists(url): os.remove(url) Logger.info('Downloaded raw.') open_file = open(url, 'a', encoding='utf-8') def join_url(base, target): target = target.split(' ') targetlist = [] for x in target: if x.find('/') != -1: x = urljoin(base, x) targetlist.append(x) else: targetlist.append(x) target = ' '.join(targetlist) return target open_file.write('\n') for x in soup.find_all('html'): fl = [] for f in x.attrs: if isinstance(x.attrs[f], str): fl.append(f'{f}="{x.attrs[f]}"') elif isinstance(x.attrs[f], list): fl.append(f'{f}="{" ".join(x.attrs[f])}"') open_file.write(f'') open_file.write('
\n') for x in soup.find_all(rel='stylesheet'): if x.has_attr('href'): x.attrs['href'] = re.sub(';', '&', urljoin(link, x.get('href'))) open_file.write(str(x)) for x in soup.find_all(): if x.has_attr('href'): x.attrs['href'] = re.sub(';', '&', urljoin(link, x.get('href'))) open_file.write('') for x in soup.find_all('style'): open_file.write(str(x)) if section is None: infoboxes = ['notaninfobox', 'portable-infobox', 'infobox', 'tpl-infobox', 'infoboxtable', 'infotemplatebox', 'skin-infobox', 'arcaeabox'] find_infobox = None for i in infoboxes: find_infobox = soup.find(class_=i) if find_infobox is not None: break if find_infobox is None: Logger.info('Found nothing...') return False # 找你妈,不找了<-咱还是回家吧 Logger.info('Found infobox...') for x in find_infobox.find_all(['a', 'img', 'span']): if x.has_attr('href'): x.attrs['href'] = join_url(link, x.get('href')) if x.has_attr('src'): x.attrs['src'] = join_url(link, x.get('src')) if x.has_attr('srcset'): x.attrs['srcset'] = join_url(link, x.get('srcset')) if x.has_attr('style'): x.attrs['style'] = re.sub(r'url\(/(.*)\)', 'url(' + link + '\\1)', x.get('style')) for x in find_infobox.find_all(class_='lazyload'): if x.has_attr('class') and x.has_attr('data-src'): x.attrs['class'] = 'image' x.attrs['src'] = x.attrs['data-src'] for x in find_infobox.find_all(class_='lazyload'): if x.has_attr('class') and x.has_attr('data-src'): x.attrs['class'] = 'image' x.attrs['src'] = x.attrs['data-src'] open_file.write(str(find_infobox)) w = 500 open_file.write('') else: for x in soup.find_all('body'): if x.has_attr('class'): open_file.write(f'') for x in soup.find_all('div'): if x.has_attr('id'): if x.get('id') in ['content', 'mw-content-text']: fl = [] for f in x.attrs: if isinstance(x.attrs[f], str): fl.append(f'{f}="{x.attrs[f]}"') elif isinstance(x.attrs[f], list): fl.append(f'{f}="{" ".join(x.attrs[f])}"') open_file.write(f'