Python实现的爬取百度贴吧图片功能完整示例

时间:2022-10-06 20:14:08

本文实例讲述了python实现的爬取百度贴吧图片功能。分享给大家供大家参考,具体如下:

?
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
#coding:utf-8
import requests
import urllib2
import urllib
```
from lxml import etree
class tieba:
  def __init__(self):
    self.tiebaname = raw_input("请输入需要爬取的贴吧:")
    self.beginpage = int(raw_input("请输入爬取的起始页:"))
    self.endpage = int(raw_input("请输入爬取的结束页:"))
    self.baseurl = "http://tieba.baidu.com"
    #self.headers = {"user-agent" : "mozilla/5.0 (windows nt 10.0; wow64) applewebkit/537.36 (khtml, like gecko) chrome/59.0.3071.86 safari/537.36"}
    self.headers = {"user-agent" : "mozilla/5.0 (compatible; msie 9.0; windows nt 6.1 trident/5.0;"} def startwork(self):
    """
      发送贴吧每一页的url请求
    """
    for page in range(self.beginpage, self.endpage + 1):
      pn = (page - 1) * 50
      keyword = {"kw" : self.tiebaname, "pn" : pn}
      kw = urllib.urlencode(keyword)
      url = self.baseurl + "/f?" + kw
      #print url
      html = self.loadrequest(url)
      self.loadpage(html)
  def loadrequest(self, url):
    """
      发送请求,返回响应
      url: 发送请求的url地址
    """
    request = urllib2.request(url, headers = self.headers)
    #request = urllib2.request(url)
    response = urllib2.urlopen(request)
    return response.read()
  def loadpage(self, html):
    """
      提取每个帖子的url,并发送请求,获取响应
      html: 贴吧每一页的html
    """
    content = etree.html(html)
    print '------'
    print content
    # xpath 返回的所有匹配成功后的结果的列表
    #pagelink_list = content.xpath("//div[@class='threadlist_lz clearfix']/div/a[@class='j_th_tit']/@href")
    pagelink_list = content.xpath("//div[@class='col2_right j_threadlist_li_right']//div/a/@href")
    pagelink_list = content.xpath("//div[@class='t_con cleafix']//div/a/@href")
    for link in pagelink_list:
      print link
      self.loadimage(self.loadrequest(self.baseurl + link))
  def loadimage(self, html):
    """
      提取帖子里用户发送的图片的url地址
      html: 每个帖子的html
    """
    content = etree.html(html)
    imagelink_list = content.xpath("//div[@class='p_content ']//img[@class='bde_image']/@src")
    for link in imagelink_list:
      self.writeimage(self.loadrequest(link), link[-10:])
  def writeimage(self, data, filename):
    """
      将图片的响应数据,写入到本地磁盘里
      data: 图片的响应数据
      filename: 文件名(图片url的后10位)
    """
    print "正在保存图片...%s" % filename
    with open(filename, "wb") as f:
      f.write(data)
if __name__ == "__main__":
  tieba = tieba()
  tieba.startwork()

希望本文所述对大家python程序设计有所帮助。

原文链接:https://blog.csdn.net/xuezhangjun0121/article/details/73719059