编写Python爬虫抓取豆瓣电影TOP100及用户头像的方法

http://movie.douban.com/top250start=0
http://movie.douban.com/top250start=25
http://movie.douban.com/top250start=50
http://movie.douban.com/top250start=75

import urllib2
import re
# ----------确定url地址池------------
pre_url = 'http://movie.douban.com/top250start='
top_urls = []
# 因为top100，每页25部电影，故为4页,从零开始
for num in range(4):
  top_urls.append(pre_url + str(num * 25))

# ------------抓取top100电影名称----------
top_content = []
top_tag = re.compile(r'<span class="title">(.+)</span>')
for url in top_urls:
  content = urllib2.urlopen(url).read()
  pre_content = re.findall(top_tag, content)
  # 过滤不符合条件的list，得到最后的top100的list
  for item in pre_content:
    if item.find(' ') == -1:
      top_content.append(item)

top_num = 1
for item in top_content:
  print 'Top' + str(top_num) + '  ' + item
  top_num += 1

# coding=utf-8
'''
本代码为自动抓取豆瓣top100电影代码
@pre_url url地址前缀，在这里为http://movie.douban.com/top250start=
@top_urls url地址池
@top_tag 为抓取电影名正则表达式
'''

import urllib2
import re

pre_url = 'http://movie.douban.com/top250start='
top_urls = []
top_tag = re.compile(r'<span class="title">(.+)</span>')
top_content = []
top_num = 1

# ----------确定url地址池------------
# 因为top100，每页25部电影，故为4页,从零开始
for num in range(4):
  top_urls.append(pre_url + str(num * 25))


# ------------抓取top100电影名称，并打印输出----------
top_tag = re.compile(r'<span class="title">(.+)</span>')
for url in top_urls:
  content = urllib2.urlopen(url).read()
  pre_content = re.findall(top_tag, content)
  # 过滤并打印输出
  for item in pre_content:
    if item.find(' ') == -1:
      print 'Top' + str(top_num) + '  ' + item
      top_num += 1

import urllib.request
import re
import time
 
#获取输入的帖子单页html
def getHtml2(url2):
  html2=urllib.request.urlopen(url2).read().decode('utf-8')
  return html2
 
#抽取图片相关列表，并下载图片
def gettopic(html2):
  reg2=r'http://www.douban.com/group/topic/\d+'
  topiclist=re.findall(reg2,html2)
  x=0
  #限制下载的图片数
  for topicurl in topiclist:
    x+=1
  return topicurl
 
 
#下载图片到本地
def download(topic_page):
  reg3=r'http://img3.douban.com/view/group_topic/large/public/.+\.jpg'
  imglist=re.findall(reg3,topic_page)
  i=1
  download_img=None
  for imgurl in imglist:
#取图片ID为文件名
    img_numlist=re.findall(r'p\d{7}',imgurl)
    for img_num in img_numlist:
       
      download_img=urllib.request.urlretrieve(imgurl,'D:\python\code\girls\%s.jpg'%img_num)
      time.sleep(1) 
      i+=1
      print(imgurl)
  return download_img
 
#调用函数
page_end=int(input('请输入结束时的页码：'))
num_end=page_end*25
num=0
page_num=1
while num<=num_end:
  html2=getHtml2('http://www.douban.com/group/kaopulove/discussion
start=%d'%num)
  topicurl=gettopic(html2)
  topic_page=getHtml2(topicurl)
  download_img=download(topic_page)
  num=page_num*25
  page_num+=1
 
else:
  print('采集完成！')