1. Taobao site law
https:. //s.taobao.com /list?spm=a21bo.2017 201867-links-0.6.5af911d9OXqjyt & q = search word & cat = 16 & style = grid & seller_type = taobao & bcoffset = 0 & s = (p -1) * 60
1.1 Note:
Data in the source code can be directly crawl; no source code, web pages but some information is hidden in the js file, then need to get caught.
1.2 Copy image URL on ebay page:
https://g-search1.alicdn.com/img/bao/uploaded/i4/imgextra/i3/224680019/O1CN01uIilBc1C0k57Kg2Kv_!!0-saturn_solar.jpg_250x250.jpg_.webp at this time we see only a small figure, not HD Fig. Resolving the Web site:
Images saved in the location of the server, do not control:
https://g-search1.alicdn.com/img/bao/uploaded/i4/imgextra/i3/224680019/:
Photo size and other important information:
jpg_250x250.jpg_.webp
The core part of the photo data: O1CN01uIilBc1C0k57Kg2Kv _ !! 0-saturn_solar
Search photos 1.3 core data in the source code:
O1CN01uIilBc1C0k57Kg2Kv _ !! 0-saturn_solar, you will find url, as shown in photo. Refresher "pic_url": "// g-search1.alicdn.com/img/bao/uploaded/i4/imgextra/i3/224680019/O1CN01uIilBc1C0k57Kg2Kv_!!0-saturn_solar.jpg". Prefixed with https, open to see high-definition big picture browser.
1.3 by regular extraction Photo URL: "pic_url": "? //(.*)"
import urllib.request
import re
keyname='短裙'
key=urllib.request.quote(keyname)
for i in range(0,5):
url='https://s.taobao.com/list?q="+key+"&cat=16&style=grid&seller_type=taobao&bcoffset=0&s='+str(i*60)
data=urllib.request.urlopen(url).read().decode('utf-8','ignore')
#正则提取
pat='pic_url":"//(.*?)"'
imageurl=re.compile(pat).findall(data)
print(imageurl)
import urllib.request
import re
keyname='短裙'
key=urllib.request.quote(keyname)
headers=('User-Agent','Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 SE 2.X MetaSr 1.0')
opener=urllib.request.build_opener()
opener.addheaders=[headers]
urllib.request.install_opener(opener)
for i in range(0,5):
url='https://s.taobao.com/list?q="+key+"&cat=16&style=grid&seller_type=taobao&bcoffset=0&s='+str(i*60)
data=urllib.request.urlopen(url).read().decode('utf-8','ignore')
#正则提取
pat='"pic_url":"//(.*?)"'
imageurl=re.compile(pat).findall(data)
print(imageurl)
import urllib.request
import re
keyname="神舟"
key=urllib.request.quote(keyname) #编码
#尝试爬取前三页内容
for i in range(0,3):
#构造页面URL
url="https://s.taobao.com/search?q="+key+"&s=44"
data=urllib.request.urlopen(url).read().decode("utf-8","ignore")
pat='pic_url":"//(.*?)"'
#获得图片URL
imagelist=re.compile(pat).findall(data)
print(imagelist)
import urllib.request
import re
keyname="神舟"
key=urllib.request.quote(keyname) #编码
#尝试爬取前三页内容
for i in range(0,3):
#构造页面URL
url="https://s.taobao.com/search?q="+key+"&s=44"
data=urllib.request.urlopen(url).read().decode("utf-8","ignore")
pat='pic_url":"//(.*?)"'
#获得图片URL
imagelist=re.compile(pat).findall(data)
for j in range(0,len(imagelist)):
thisimg=imagelist[j]
#构造图片URL
thisimgurl="http://"+thisimg
file=" F:/jupyterpycodes/python_pachongfenxi/result/taobaoIMG/"+str(i)+str(j)+".jpg"