狮子座大数据分析（python爬虫版）

十二星座爱情性格 - 星座屋

首先找到一个星座网站，作为基础内容，来获取信息

网页爬取与信息提取

我们首先利用爬虫技术（如 Python 中的 requests 与 BeautifulSoup 库）获取页面内容。该页面（xzw.com/astro/leo/）中，除了狮子座基本属性外，还有两个重点部分：

• 狮子座女生：摘要中提到“特点：心地善良、爱心丰富”，“弱点：喜欢引人注目”，“爱情：不太懂得疼爱对方”。
• 狮子座男生：摘要中提到“特点：热情、组织能力、正义感”，“弱点：高傲、虚荣心”，“爱情：追求轰轰烈烈的爱情”。

通过解析这些文字，我们可以归纳：

• 狮子座男生：性格热情、具备较强的组织能力和正义感，但有时表现出高傲和虚荣，热衷于追求激情四溢的爱情。
• 狮子座女生：性格温暖、心地善良且富有爱心，但喜欢吸引他人注意，在爱情中可能表现得不够细腻体贴。

import requests
from bs4 import BeautifulSoup
import timebase_url = "https://www.xzw.com/astro/leo/"
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)"
}collected_texts = []
visited_urls = set()def scrape_page(url):global collected_textsif url in visited_urls:returntry:response = requests.get(url, headers=headers, timeout=10)response.encoding = 'utf-8'soup = BeautifulSoup(response.text, 'html.parser')page_text = soup.get_text(separator="\n", strip=True)collected_texts.append(page_text)visited_urls.add(url)  # 标记该 URL 已访问print(f"已爬取: {url} (当前累计 {len(collected_texts)} 条文本)")for link in soup.find_all('a', href=True):full_link = link['href']if full_link.startswith("/"):full_link = "https://www.xzw.com" + full_linkif full_link.startswith(base_url) and full_link not in visited_urls:if len(collected_texts) >= 1000:returntime.sleep(1)scrape_page(full_link)except Exception as e:print(f"爬取 {url} 失败: {e}")scrape_page(base_url)with open("test.txt", "w", encoding="utf-8") as file:file.write("\n\n".join(collected_texts))print("🎉 爬取完成，数据已保存到 test.txt 文件！")

将爬取到的数据存入test.txt中后，进行分析
 

import jieba
import re
from collections import Counterdef read_file(file_path):with open(file_path, 'r', encoding='utf-8') as f:text = f.read()return textdef clean_text(text):text = re.sub(r'\s+', '', text)text = re.sub(r'[^\u4e00-\u9fa5]', '', text)return textdef tokenize(text):words = jieba.lcut(text)return wordsdef count_words(words):return Counter(words)POSITIVE_WORDS = {"自信", "阳光", "大方", "慷慨", "勇敢", "领导", "果断", "豪爽", "热情", "友善","善良"}
NEGATIVE_WORDS = {"自负", "霸道", "固执", "急躁", "冲动", "强势", "高傲", "爱面子", "争强好胜", "以自我为中心"}def analyze_personality(word_counts):total_words = sum(word_counts.values())pos_count = sum(word_counts[word] for word in POSITIVE_WORDS if word in word_counts)neg_count = sum(word_counts[word] for word in NEGATIVE_WORDS if word in word_counts)pos_percent = (pos_count / total_words) * 100 if total_words > 0 else 0neg_percent = (neg_count / total_words) * 100 if total_words > 0 else 0neutral_percent = 100 - pos_percent - neg_percentreturn pos_percent, neg_percent, neutral_percentdef evaluate_personality(pos_percent, neg_percent):if pos_percent > neg_percent:conclusion = "狮子座整体评价较好，正面特质占比更高。"elif neg_percent > pos_percent:conclusion = "狮子座评价存在较多负面特质，但也有正面评价。"else:conclusion = "狮子座评价较为中立，正负面评价相当。"return conclusiondef main():text = read_file("test.txt")text = clean_text(text)words = tokenize(text)word_counts = count_words(words)pos_percent, neg_percent, neutral_percent = analyze_personality(word_counts)conclusion = evaluate_personality(pos_percent, neg_percent)print("🔍 狮子座性格评价分析：")print(f"✅ 正面评价占比：{pos_percent:.2f}%")print(f"❌ 负面评价占比：{neg_percent:.2f}%")print(f"⚖ 中立评价占比：{neutral_percent:.2f}%")print(f"📢 结论：{conclusion}")if __name__ == "__main__":main()

进行评价：

import jieba
import jieba.posseg as pseg 
import re
from collections import Counter
from wordcloud import WordCloud
import matplotlib.pyplot as pltdef read_file(file_path):with open(file_path, 'r', encoding='utf-8') as f:text = f.read()return textdef clean_text(text):text = re.sub(r'\s+', '', text)  # 去除空格和换行符text = re.sub(r'[^\u4e00-\u9fa5]', '', text)  # 只保留中文return textdef tokenize(text):words = pseg.lcut(text)  # 使用 jieba 进行分词并标注词性adjectives = [word for word, flag in words if flag == 'a']  # 只保留形容词return adjectivesdef count_words(words):return Counter(words)def generate_wordcloud(word_counts):wordcloud = WordCloud(font_path='msyh.ttc', width=800, height=600, background_color='white').generate_from_frequencies(word_counts)plt.figure(figsize=(10, 8))plt.imshow(wordcloud, interpolation='bilinear')plt.axis('off')plt.show()def top_words(word_counts, top_n=10):return dict(word_counts.most_common(top_n))def main():text = read_file("test.txt")text = clean_text(text)words = tokenize(text)word_counts = count_words(words)top_n_words = top_words(word_counts, top_n=10)generate_wordcloud(top_n_words)if __name__ == "__main__":main()

多种图：

import matplotlib
matplotlib.use('TkAgg')
import matplotlib.pyplot as plt
import jieba
import jieba.posseg as pseg
import re
from collections import Counter
from wordcloud import WordCloud# 设置支持中文的字体（以黑体为例）
plt.rcParams['font.sans-serif'] = ['SimHei']
# 防止负号显示为方块
plt.rcParams['axes.unicode_minus'] = Falsedef read_file(file_path):with open(file_path, 'r', encoding='utf-8') as f:text = f.read()return textdef clean_text(text):text = re.sub(r'\s+', '', text)text = re.sub(r'[^\u4e00-\u9fa5]', '', text)return textdef tokenize(text):# 使用 jieba 对文本进行分词和词性标注words = pseg.lcut(text)# 仅保留形容词相关词性（例如 'a' 表示形容词），过滤掉名词等其它词性adjectives = [word for word, flag in words if flag in ['a', 'ad', 'an', 'ag']]return adjectivesdef count_words(words):return Counter(words)def generate_wordcloud(word_counts):wordcloud = WordCloud(font_path='msyh.ttc', width=800, height=600, background_color='white').generate_from_frequencies(word_counts)plt.figure(figsize=(10, 8))plt.imshow(wordcloud, interpolation='bilinear')plt.axis('off')plt.title("狮子座相关评价词云", fontsize=20, fontweight='bold', family='Microsoft YaHei')plt.show()def plot_bar_chart(word_counts, top_n=10):top_words = dict(word_counts.most_common(top_n))plt.figure(figsize=(10, 6))plt.bar(top_words.keys(), top_words.values(), color='skyblue')plt.title("狮子座最常见形容词柱状图", fontsize=18, fontweight='bold', family='Microsoft YaHei')plt.xlabel("形容词", fontsize=14, family='Microsoft YaHei')plt.ylabel("频率", fontsize=14, family='Microsoft YaHei')plt.xticks(rotation=45)plt.show()def plot_horizontal_bar_chart(word_counts, top_n=10):top_words = dict(word_counts.most_common(top_n))plt.figure(figsize=(10, 6))plt.barh(list(top_words.keys()), list(top_words.values()), color='lightcoral')plt.title("狮子座最常见形容词条形图", fontsize=18, fontweight='bold', family='Microsoft YaHei')plt.xlabel("频率", fontsize=14, family='Microsoft YaHei')plt.ylabel("形容词", fontsize=14, family='Microsoft YaHei')plt.show()def plot_pie_chart(word_counts, top_n=5):top_words = dict(word_counts.most_common(top_n))plt.figure(figsize=(8, 8))plt.pie(top_words.values(), labels=top_words.keys(), autopct='%1.1f%%', startangle=140,colors=['skyblue', 'lightgreen', 'lightcoral', 'gold', 'lightpink'])plt.title("狮子座最常见形容词饼状图", fontsize=18, fontweight='bold', family='Microsoft YaHei')plt.show()def main():text = read_file("test.txt")text = clean_text(text)words = tokenize(text)word_counts = count_words(words)generate_wordcloud(word_counts)plot_bar_chart(word_counts)plot_horizontal_bar_chart(word_counts)plot_pie_chart(word_counts)if __name__ == "__main__":main()