数据爬取源码

详细过程大家可以在其他帖子中看到.
这里采用python2.7以及原生库urllib2和re库进行爬取.

# coding=utf-8
import urllib2
import re
import time


def get_Request(page):
   url = 'https://movie.douban.com/top250'
   headers = {
       'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.78 Safari/537.36',
       'Host': 'movie.douban.com',
   }
   req = urllib2.Request(url + '?start=' + str(page) + '&filter=', headers=headers)
   res = urllib2.urlopen(req).read()

   return res


def get_content(res):
   total = re.findall('<div class="item">([\s\S]+?)</div>\s+</li>', res, re.S)
   all_data = list()
   for item in total:
       try:
           title = re.findall('<span class="title">(.*?)</span>', item)
           count = re.findall('<em class="">(\d+)</em>', item)
           director = re.findall('<p class="">\s+导演:\s+(.*?)&nbsp;&nbsp;&nbsp;', item)
           other = re.findall('<br>\s+(\d{4,})&nbsp;/&nbsp;(.*?)&nbsp;/&nbsp;(.*?)\s+</p>', item)
           score = re.findall('<span class="rating_num" property="v:average">(\d\.\d+)</span>', item)
           name = title[0]
           other_name = ''
           counts = count[0]
           direct = director[0]
           year = other[0][0]
           country = other[0][1].replace(' ', '/'),
           type = other[0][2].replace(' ', '/'),
           scores = score[0],
           if len(title) > 1:
               other_name = title[1].replace('&nbsp;/&nbsp;', '').replace(',', ' '),
           else:
               title.append('0')
               other_name = title[1]
           data = dict(
               name=name,
               other_name=other_name[0],
               director=direct,
               year=year,
               country=country[0],
               type=type[0],
               score=scores[0],
           )
           all_data.append(data)
       except:
           all_data.append(data)

   return all_data


def save_data(data):
   value = ''
   with open('data.txt', 'a') as f:
       for line in data:
           for values in ['name', 'other_name', 'director', 'year', 'country', 'type', 'score']:
               if values == 'score':
                   value += line[values]
               else:
                   value += line[values] + ','
           f.write(str(value) + '\n')
           print value + '\n'
           value = ''
   f.close()


def run(page):
   res = get_Request(page)
   data = get_content(res)
   save_data(data)


if __name__ == "__main__":
   page = 0
   while page < 250:
       run(page=page)
       page += 25
       time.sleep(0.5)
   print 'finished data crawl'

数据分析

影片类型分析

这里对于爬取下来的数据集,并对类型中的"/"进行切割.
分割前: