本文實例講述了python實現的爬取百度貼吧圖片功能。分享給大家供大家參考，具體如下：
|
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-8import requestsimport urllib2import urllib```from lxml import etreeclass tieba: def __init__(self): self.tiebaname = raw_input("請輸入需要爬取的貼吧:") self.beginpage = int(raw_input("請輸入爬取的起始頁：")) self.endpage = int(raw_input("請輸入爬取的結束頁：")) 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): """ 發送貼吧每一頁的url請求 """ 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): """ 發送請求，返回響應 url: 發送請求的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): """ 提取每個帖子的url，并發送請求，獲取響應 html: 貼吧每一頁的html """ content = etree.html(html) print '------' print content # xpath 返回的所有匹配成功后的結果的列表 #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): """ 提取帖子里用戶發送的圖片的url地址 html: 每個帖子的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): """ 將圖片的響應數據，寫入到本地磁盤里 data: 圖片的響應數據 filename: 文件名(圖片url的后10位) """ print "正在保存圖片...%s" % filename with open(filename, "wb") as f: f.write(data)if __name__ == "__main__": tieba = tieba() tieba.startwork() |
希望本文所述對大家python程序設計有所幫助。
原文鏈接：https://blog.csdn.net/xuezhangjun0121/article/details/73719059
