需求分析:
"我想要图片,我又不想上网搜“
“最好还能自动下载”
……
这就是需求,实现两个功能,一是搜索图片,二是自动下载
主要工作在分析网页和数据处理
import requests
import os
import re
def req(url):
headers = {'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.109 Safari/537.36'}
try:
response = requests.get(url,headers=headers)
except Exception as e:
print('获取失败',e)
else:
html = response.text
downloadpic(html,headers)
def downloadpic(html,headers):
pic_url = re.findall('"objURL":"(.*?)"',html,re.S)
count=0
for each in pic_url:
try:
pic=requests.get(each,headers=headers)
print(pic)
except requests.exceptions.ConnectionError as f:
print('图片无法下载')
except Exception as e:
print(e)
else:
pic.raise_for_status()
if not os.path.exists(savedir):
os.makedirs(savedir)
else:
tail = each.split(".")[-1]
if tail not in ['png', 'jpg', 'gif', 'jpeg']:
continue
count+=1
filename=strpic+ str(count)+tail
fullfilename = os.path.join(savedir,filename)
with open(fullfilename,'wb') as f:
f.write(pic.content)
if __name__ == '__main__':
strpic = input('please input str:')
url = 'http://image.baidu.com/search/index?tn=baiduimage&ps=1&ct=201326592&lm=-1&cl=2&nc=1&ie=utf-8&word=' + strpic
savedir='/home/kiosk/Desktop/pictures'
req(url)