爬虫小案例:豆瓣Top250电影
获取豆瓣Top250电影列表,然后给自己发邮件
直接上代码:
import requests,os,csv,time,smtplib from email.mime.text import MIMEText from email.utils import formataddr from email.header import Header from email.header import make_header from email.mime.multipart import MIMEMultipart from bs4 import BeautifulSoup # 数据写入到文件 file_path = os.getcwd() + "/豆瓣Top250电影.csv" if not os.path.isfile(file_path): # 编码utf-8-sig:支持python3,不支持python2 with open(file_path, ‘w‘, newline=‘‘, encoding=‘utf-8-sig‘) as f: writer = csv.writer(f) writer.writerow([‘排名‘, ‘电影名称‘, ‘上映年份‘, ‘地区‘, ‘类型‘, ‘评分‘, ‘推荐语‘, ‘链接‘]) # 电影列表 filmlist = [] for x in range(10): url = ‘https://movie.douban.com/top250?start={}&filter=‘.format(x * 25) # 为躲避反爬机制,伪装成浏览器的请求头 headers = {‘User-Agent‘:‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36 OPR/65.0.3467.78 (Edition Baidu)‘} res = requests.get(url, headers=headers) if res.status_code == 200: print(‘正获取第{}页电影数据...‘.format(x+1)) htmltext = res.text soup = BeautifulSoup(htmltext, ‘html.parser‘) ol = soup.find(‘ol‘, class_=‘grid_view‘) for li in ol.find_all(‘li‘): # 排名 num = li.find(‘div‘, class_=‘pic‘).find(‘em‘).text info = li.find(‘div‘, class_=‘info‘) # 标题 title = [] title_spans = info.find(‘div‘, class_=‘hd‘).find(‘a‘).find_all(‘span‘) for title_span in title_spans: title.append(title_span.text) title = ‘‘.join(title) # 链接 link = info.find(‘div‘, class_=‘hd‘).find(‘a‘)[‘href‘] # 评分 rating_num = info.find(‘span‘, class_=‘rating_num‘).text # 推荐语 inq = info.find(‘span‘, class_=‘inq‘).text # 上映时间、地区、类型 bd = info.find(‘div‘, class_=‘bd‘).find(‘p‘).contents[2] bd = bd.split(‘/‘) # 保存到文件上 with open(file_path, ‘a‘, newline=‘‘, encoding=‘utf-8-sig‘) as f: writer = csv.writer(f) writer.writerow([num, title, bd[0].strip(), bd[1].strip(), bd[2].strip(), rating_num, inq, link]) filmlist.append("{0}.{1}:{2}/{3}/{4},评分:{5},推荐语:{6},链接:{7}".format(num,title,bd[0].strip(),bd[1].strip(),bd[2].strip(),rating_num,inq,link)) time.sleep(0.75) # print(num) # print(title) # print(link) # print(rating_num) # print(inq) # print(bd) # print(‘{0}.{1} —— {2},推荐语:{3},链接:{4}‘.format(rating_num,title,inq,link)) else: print(‘请求失败!‘) # 发送邮件 my_sender = ‘xxx‘ # 发件人邮箱账号 my_pass = ‘xxx‘ # 发件人邮箱密码 try: print(time.strftime(‘%Y-%m-%d %H:%M:%S‘, time.localtime()) + ":准备发送邮件") # 创建一个带附件的实例 # 使用多形式组合 msg = MIMEMultipart() msg[‘From‘] = formataddr(["ljq", my_sender]) # 括号里的对应发件人邮箱昵称、发件人邮箱账号 msg[‘To‘] = formataddr(["lsjljq", ‘‘]) # 括号里的对应收件人邮箱昵称、收件人邮箱账号 # 邮件标题 subject = ‘豆瓣Top250电影‘ msg[‘Subject‘] = Header(subject, ‘utf-8‘) # 邮件正文内容 contenttext = "\n".join(filmlist) msg.attach(MIMEText(contenttext, ‘plain‘, ‘utf-8‘)) # 构造附件1,传送当前目录下的 test.txt 文件 att1 = MIMEText(open(‘豆瓣Top250电影.csv‘, ‘rb‘).read(), ‘base64‘, ‘utf-8‘) # 文件名如果是中文,则需要转化一下 att1["Content-Type"] = ‘application/octet-stream;name="{0}"‘.format(make_header([(‘豆瓣Top250电影‘, ‘UTF-8‘)]).encode(‘UTF-8‘)) # 这里的filename可以任意写,写什么名字,邮件中显示什么名字 att1["Content-Disposition"] = ‘attachment; filename="{0}.csv"‘.format(make_header([(‘豆瓣Top250电影‘, ‘UTF-8‘)]).encode(‘UTF-8‘)) msg.attach(att1) print(time.strftime(‘%Y-%m-%d %H:%M:%S‘, time.localtime()) + ":正连接邮件服务器...") server = smtplib.SMTP_SSL("smtp.exmail.qq.com", 465) # 发件人邮箱中的SMTP服务器,端口是25 print(time.strftime(‘%Y-%m-%d %H:%M:%S‘, time.localtime()) + ":登录中...") server.login(my_sender, my_pass) # 括号中对应的是发件人邮箱账号、邮箱密码 print(time.strftime(‘%Y-%m-%d %H:%M:%S‘, time.localtime()) + ":正在发送邮件...") server.sendmail(my_sender, [‘‘], msg.as_string()) # 括号中对应的是发件人邮箱账号、收件人邮箱账号、发送邮件 server.quit() # 关闭连接 print(‘邮件发送成功!‘) except Exception as err: print(‘邮件发送失败!:{0}‘.format(err))