实例如下所示：
|
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
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
|
import requestsimport re,sys,osimport jsonimport threadingimport pprintclass spider: def __init__(self,sid,name): self.id = sid self.headers = { "Accept":"text/html,application/xhtml+xml,application/xml;", "Accept-Encoding":"gzip", "Accept-Language":"zh-CN,zh;q=0.8", "Referer":"http://www.example.com/", "User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36" } self.name=name def openurl(self,url): self.request = requests.get(url,headers = self.headers) if self.request.ok: return self.request.text def matchs(self): tmall_exp = r"Setup\(([\s\S]+?)\);"### 匹配商品数据的正则 detail= r"src=\"(https://img\S+?[jpgifn]+?)\"" ###匹配 商品详情图的正则 html = self.openurl("https://detail.tmall.com/item.htm?id=%s"%self.id) data = re.findall(tmall_exp,html) data = json.loads(data[0]) main_img = data['propertyPics'] ## 这里包括了主图和颜色图的地址 color_data =data['valItemInfo'] ['skuList'] ### 这里获得商品的颜色信息列表 包括颜色编码 颜色名称,商品skuID detail_html = self.openurl("http:"+data['api']["httpsDescUrl"]) detail_image = re.findall(detail,detail_html) self.newdata={"MAIN":main_img['default'],"DETAIL":detail_image,"id":self.id,} psvs = [] self.newdata['COLOR']=[] for v in range(len(color_data)): if ";"in color_data[v]["pvs"]: psv = color_data[v]['pvs'][color_data[v]['pvs'].find(";")+1:] else: psv = color_data[v]['pvs'] if psv in psvs: continue psvs.append(psv) self.newdata['COLOR'].append({color_data[v]["names"]:main_img[";"+psv+";"]}) pprint.pprint(self.newdata) return self.newdata def download(self): if len(self.newdata)>0: for x in range(len(self.newdata['MAIN'])): threading.Thread(target=self.download_main,args=(self.newdata['MAIN'][x],x)).start() for x in self.newdata['COLOR']: threading.Thread(target=self.download_color,args=(x,)).start() for x in range(len(self.newdata['DETAIL'])): threading.Thread(target=self.download_detail,args=(self.newdata['DETAIL'][x],x)).start() return def download_main(self,url,index): try: img = requests.get("http:"+url,stream=True,headers = self.headers,timeout=10) except: print(sys.exc_info()) return if img.ok: if not os.path.exists(self.name+"/main"): try: os.makedirs(self.name+"/main") except: pass imgs = open(self.name+"/main/%s.jpg"%index,"wb") imgs.write(img.content) imgs.close() def download_color(self,url): try: img = requests.get("http:"+url[list(url.keys())[0]][0],stream=True,headers = self.headers,timeout=10) except: print(sys.exc_info()) return if img.ok: if not os.path.exists(self.name+"/color"): try: os.makedirs(self.name+"/color") except: pass if "/"in list(url.keys())[0]: color = list(url.keys())[0].replace("/","_") elif "\\" in list(url.keys())[0]: color = list(url.keys())[0].replace("\\","_") else: color = list(url.keys())[0] imgs = open(self.name+"/color/%s.jpg"%color,"wb") imgs.write(img.content) imgs.close() def download_detail(self,url,index): try: img = requests.get(url,stream=True,headers = self.headers,timeout=10) except: print(sys.exc_info()) return if img.ok: if not os.path.exists(self.name+"/detail"): try: os.makedirs(self.name+"/detail") except: pass imgs = open(self.name+"/detail/%s.jpg"%index,"wb") imgs.write(img.content) imgs.close() if __name__ =="__main__": sid = 528766269341 ## 这里输入天猫宝贝ID taobao = spider(sid,"下载图片/T") taobao.matchs() taobao.download() |
以上这篇python 爬虫一键爬取 淘宝天猫宝贝页面主图颜色图和详情图的教程就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持服务器之家。
原文链接：https://blog.csdn.net/mzbqhbc12/article/details/54992954
