/* 以下内容为Python代码 */ import requests import re from langdetect import detect search_word = "macalan" url = f"https://www.google.com/search?q={search_word}&tbm=nws" headers = { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"} response = requests.get(url, headers=headers) html = response.text texts = re.findall(r'

(.*?)

', html) clean_texts = [] for text in texts: clean_text = re.sub( r'[\U0001f600-\U0001f650]|[\U0001f300-\U0001f5ff]|[\U0001f680-\U0001f6ff]|[\U0001f1e0-\U0001f1ff]', '', text[1], flags=re.UNICODE) if clean_text: clean_texts.append(clean_text) final_text = "" for text in clean_texts: if detect(text) == 'pt': if len(final_text) < 200: final_text += text + " " else: break print(final_text.strip())