python爬取豆瓣电影top250并可视化分析

好的，以下是Python爬取豆瓣电影Top250并可视化分析的代码实现： 首先，我们需要导入必要的库： ```python import requests from bs4 import BeautifulSoup import pandas as pd import matplotlib.pyplot as plt ``` 接着，我们需要编写爬取Top250电影信息的函数： ```python def get_movies(): 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'} movie_list = [] for i in range(0, 250, 25): url = 'https://movie.douban.com/top250?start={}&filter='.format(i) response = requests.get(url, headers=headers) soup = BeautifulSoup(response.text, 'html.parser') movies = soup.find_all('div', class_='info') for movie in movies: title = movie.find('span', class_='title').text director = movie.find('div', class_='bd').p.text.split('\n')[1].strip().split(':')[1] star = movie.find('div', class_='star').text.strip().split('\n')[0] quote = movie.find('span', class_='inq').text if movie.find('span', class_='inq') else '' movie_list.append({'title': title, 'director': director, 'star': star, 'quote': quote}) return movie_list ``` 该函数使用requests库向豆瓣电影Top250网页发送请求，并使用BeautifulSoup库解析网页内容。然后，它从网页中找到所有电影信息所在的div标签，并使用循环遍历每个电影，并提取出电影的标题、导演、评分和简介。最后，函数将所有电影信息存储在一个列表中，并返回该列表。 接下来，我们可以调用该函数并将电影信息存储在一个DataFrame中： ```python movies = get_movies() df = pd.DataFrame(movies) ``` 现在，我们可以使用pandas库对数据进行分析和可视化。例如，我们可以计算每个导演的电影数量，并使用matplotlib库绘制一个水平条形图： ```python director_count = df['director'].value_counts().sort_values(ascending=True) plt.barh(director_count.index, director_count.values) plt.title('Number of Movies by Director') plt.xlabel('Number of Movies') plt.show() ``` 我们还可以计算不同评分的电影数量，并使用饼图将其可视化： ```python star_count = df['star'].value_counts() plt.pie(star_count.values, labels=star_count.index, autopct='%1.1f%%') plt.title('Distribution of Movie Ratings') plt.show() ``` 最后，我们可以将所有电影信息保存到一个CSV文件中： ```python df.to_csv('movies.csv', index=False) ``` 完整代码如下： ```python import requests from bs4 import BeautifulSoup import pandas as pd import matplotlib.pyplot as plt def get_movies(): 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'} movie_list = [] for i in range(0, 250, 25): url = 'https://movie.douban.com/top250?start={}&filter='.format(i) response = requests.get(url, headers=headers) soup = BeautifulSoup(response.text, 'html.parser') movies = soup.find_all('div', class_='info') for movie in movies: title = movie.find('span', class_='title').text director = movie.find('div', class_='bd').p.text.split('\n')[1].strip().split(':')[1] star = movie.find('div', class_='star').text.strip().split('\n')[0] quote = movie.find('span', class_='inq').text if movie.find('span', class_='inq') else '' movie_list.append({'title': title, 'director': director, 'star': star, 'quote': quote}) return movie_list movies = get_movies() df = pd.DataFrame(movies) director_count = df['director'].value_counts().sort_values(ascending=True) plt.barh(director_count.index, director_count.values) plt.title('Number of Movies by Director') plt.xlabel('Number of Movies') plt.show() star_count = df['star'].value_counts() plt.pie(star_count.values, labels=star_count.index, autopct='%1.1f%%') plt.title('Distribution of Movie Ratings') plt.show() df.to_csv('movies.csv', index=False) ```

好的，我可以为您提供代码参考。首先需要安装相关的库：requests、BeautifulSoup、pandas、matplotlib。 ```python import requests from bs4 import BeautifulSoup import pandas as pd import matplotlib.pyplot as plt # 获取电影信息 def get_movie_info(url): 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) soup = BeautifulSoup(response.text, 'html.parser') movie_list = soup.find_all('div', class_='hd') info_list = [] for movie in movie_list: title = movie.a.span.text.strip() # 电影名称 link = movie.a['href'] # 电影链接 rating = movie.parent.find('span', class_='rating_num').text # 评分 rating_num = movie.parent.find('div', class_='star').find_all('span')[-1].text[:-3] # 评分人数 info_list.append([title, link, float(rating), int(rating_num)]) return info_list # 获取所有电影信息 def get_all_movie_info(): url = 'https://movie.douban.com/top250' info_list = [] for i in range(10): page_url = url + f'?start={i*25}' info_list += get_movie_info(page_url) return info_list # 可视化电影评分分布 def plot_rating_distribution(data): plt.hist(data, bins=10, range=(0, 10), color='b', alpha=0.5) plt.xlabel('Rating') plt.ylabel('Number of Movies') plt.title('Distribution of Movie Ratings') plt.savefig('rating_distribution.png') plt.show() # 存储电影信息到csv文件 def save_to_csv(data): df = pd.DataFrame(data, columns=['Title', 'Link', 'Rating', 'RatingNum']) df.to_csv('movie_info.csv', index=False) if __name__ == '__main__': movie_info = get_all_movie_info() save_to_csv(movie_info) ratings = [info[2] for info in movie_info] plot_rating_distribution(ratings) ``` 以上代码中，`get_movie_info(url)`函数用于获取单页电影信息，`get_all_movie_info()`函数用于获取所有电影信息，`save_to_csv(data)`函数用于将数据存储到csv文件中，`plot_rating_distribution(data)`函数用于绘制电影评分分布直方图。最后在主函数中调用这些函数即可。