个人的第一个python爬虫程序，如果错误，请指正。
程序用于抓取豆瓣电影正在热播的电影信息，详细代码如下所示：
#!/usr/bin/python# -*- coding: UTF-8 -*-import os,requestsfrom bs4 import BeautifulSoupdef get_url_page(url,headers):try:response = requests.get(url,headers = headers)if response.status_code == 200:return response.textelse:raise Exception('获取页面信息异常，response_stauts = %s '%response.status_code)except RequestException: return Noneif __name__ == '__main__':print('采集豆瓣电影信息') ##获取页面信息url = '/'headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:47.0) Gecko/0101 Firefox/47.0'} page_content = get_url_page(url,headers)##切换路径folder_path,file_name = os.path.split(os.path.realpath(__file__)) os.chdir(folder_path)##存储网页htmlhtml_file = os.path.splitext(file_name)[0] + '.html' file = open(html_file,'w+',encoding='utf-8')file.truncate() file.write(page_content)file.close()##使用beautifulsoup解析soup = BeautifulSoup(open(html_file,encoding='utf-8'),features='html.parser')##soup = BeautifulSoup(page_content,'lxml')for i,row in enumerate(soup.body.findAll('div',attrs = {"id":"screening"})): movies_dict = {} for j,col in enumerate(row.findAll('li',attrs = {"class":"ui-slide-item"})): if 'data-director' in col.attrs:##返回上级目录os.chdir(folder_path)movies_path = os.path.join(folder_path,col.ul.li.a.img['alt']) if not os.path.isdir(movies_path):os.mkdir(movies_path)##进入电影目录,下载电影图片 os.chdir(movies_path)movie_name = col.ul.li.a.img['alt']img_link = col.ul.li.a.img['src']img = requests.get(img_link) if img.status_code == 200:open('1.jpg', 'wb').write(img.content) # 写入文件else:print('图片不存在')#写入电影信息fo = open(movie_name + '.txt','w',encoding='utf-8')fo.truncate()fo.writelines('电影标题：' + col['data-title'] + '\n')fo.writelines('导演：' + col['data-director'] + '\n')fo.writelines('时长：' + col['data-duration'] + '\n') fo.writelines('国家：' + col['data-region'] + '\n') fo.writelines('评分：' + col['data-rate'] + '\n')fo.close()
代码运行效果如下所示：
