Skip to content

Commit 1182e39

Browse files
javasmalljavasmall
committed
update
1 parent 127b363 commit 1182e39

4 files changed

Lines changed: 94 additions & 0 deletions

File tree

‎爬虫/Include/趣味学习图片下载/bizhi.jpg‎

30.3 KB
Loading

‎爬虫/Include/趣味学习图片下载/downloadtest.py‎

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
1+
2+
import requests
3+
url='https://weiliicimg9.pstatp.com/weili/ms/57436992794921884.webp'
4+
url2='https://icweiliimg9.pstatp.com/weili/ms/256690017602371867.webp'
5+
r=requests.get(url)
6+
print(r.status_code)
7+
with open('/img/bizhi.jpg', 'wb') as f:
8+
f.write(r.content)

‎爬虫/Include/趣味学习图片下载/imgget.py‎

Lines changed: 68 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,68 @@
1+
import requests
2+
from urllib import parse
3+
from bs4 import BeautifulSoup
4+
import re
5+
import json
6+
header = {
7+
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36',
8+
'Cookie': 'wluuid=66; ',
9+
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3',
10+
'Accept-encoding': 'gzip, deflate, br',
11+
'Accept-language': 'zh-CN,zh;q=0.9',
12+
'Cache-Control': 'max-age=0',
13+
'connection': 'keep-alive'
14+
, 'Host': 'stock.tuchong.com',
15+
'Upgrade-Insecure-Requests': '1'
16+
}
17+
def mkdir(path):
18+
import os# 引入模块
19+
path = path.strip()# 去除首位空格
20+
path = path.rstrip("\\") # 去除尾部 \ 符号
21+
isExists = os.path.exists(path) # 判断路径是否存在 # 存在 True # 不存在 False
22+
if not isExists: # 判断结果
23+
os.makedirs(path)# 如果不存在则创建目录 # 创建目录操作函数
24+
return True#print (path + ' 创建成功')
25+
else:
26+
# 如果目录存在则不创建，并提示目录已存在
27+
#print(path + ' 目录已存在')
28+
return False
29+
def downloadimage(imageid,imgname):
30+
url = 'https://weiliicimg9.pstatp.com/weili/ms/'+str(imageid)+'.webp'
31+
url2 = 'https://icweiliimg9.pstatp.com/weili/ms/'+str(imageid)+'.webp'
32+
b=False
33+
r = requests.get(url)
34+
print(r.status_code)
35+
if(r.status_code!=200):
36+
r=requests.get(url2)
37+
with open(imgname+'.jpg', 'wb') as f:
38+
f.write(r.content)
39+
print(imgname+" 下载成功")
40+
def getText(text):
41+
texturl = parse.quote(text)
42+
url="https://stock.tuchong.com/search?term="+texturl+"&use=0"
43+
req=requests.get(url,headers=header)
44+
soup=BeautifulSoup(req.text,'lxml')
45+
js=soup.select('script')
46+
js=js[4]
47+
print(js)
48+
pattern = re.compile(r'window.hits = (\[)(.*)(\])')
49+
va = pattern.search(str(js)).group(2)#解析js内容
50+
print(va)
51+
va = va.replace('{', '{').replace('}', '},,')
52+
print(va)
53+
va = va.split(',,,')
54+
print(va)
55+
index = 1
56+
for data in va:
57+
try:
58+
dict = json.loads(data)
59+
print(dict)
60+
imgname='img/'+text+'/'+dict['title']+str(index)
61+
index+=1
62+
mkdir('img/'+text)
63+
imgid=dict['imageId']
64+
downloadimage(imgid,imgname)
65+
except Exception as e:
66+
print(e)
67+
if __name__ == '__main__':
68+
getText(text=input('输入关键词:'))

0 commit comments

Comments
 (0)