## 深度学习模型训练极大的依赖数据,当数据量不够时,可通过网络爬虫从网上爬取数据。下面以爬取刘亦菲和刘德华图片数据为例介绍爬虫:
## 代码使用步骤如下:
1. 在name.txt中输入你要爬取的关键词,我输入的为刘亦菲和刘德华(不用创建文件夹,文件夹是代码生成的)。
刘亦菲
刘德华
import re
import requests
from urllib import error
from bs4 import BeautifulSoup
import os
num = 0
numPicture = 0
file = ''
List = []
def Find(url):
global List
print('正在检测图片总数,请稍等.....')
t = 0
i = 1
s = 0
while t < 1000:
Url = url + str(t)
try:
Result = requests.get(Url, timeout=7)
except BaseException:
t = t + 60
#import pdb;pdb.set_trace()
continue
else:
result = Result.text
pic_url = re.findall('"objURL":"(.*?)",', result, re.S) # 先利用正则表达式找到图片url
s += len(pic_url)
if len(pic_url) == 0:
#import pdb;pdb.set_trace()
break
else:
List.append(pic_url)
t = t + 60
return s
def recommend(url):
Re = []
try:
html = requests.get(url)
except error.HTTPError as e:
return
else:
html.encoding = 'utf-8'
bsObj = BeautifulSoup(html.text, 'html.parser')
div = bsObj.find('div', id='topRS')
if div is not None:
listA = div.findAll('a')
for i in listA:
if i is not None:
Re.append(i.get_text())
return Re
def dowmloadPicture(html, keyword):
global num
# t =0
pic_url = re.findall('"objURL":"(.*?)",', html, re.S) # 先利用正则表达式找到图片url
print('找到关键词:' + keyword + '的图片,即将开始下载图片...')
for each in pic_url:
print('正在下载第' + str(num + 1) + '张图片,图片地址:' + str(each))
try:
if each is not None:
pic = requests.get(each, timeout=7)
else:
continue
except BaseException:
print('错误,当前图片无法下载')
continue
else:
string = os.path.join(file, str(num) + '.jpg')
fp = open(string, 'wb')
fp.write(pic.content)
fp.close()
num += 1
if num >= numPicture:
return
if __name__ == '__main__':
tm = int(input('请输入每类图片的下载数量 '))
numPicture = tm
line_list = []
with open('name.txt', encoding='utf-8') as file:
line_list = [k.strip() for k in file.readlines()]
#import pdb;pdb.set_trace()
for word in line_list:
url = 'http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=' + word + '&pn='
tot = Find(url)
Recommend = recommend(url) # 记录相关推荐
print('经过检测%s类图片共有%d张' % (word, tot))
file = word
y = os.path.exists(file)
if y == 1:
print('该文件已存在,请重新输入')
file = word
os.mkdir(file)
else:
os.mkdir(file)
t = 0
tmp = url
while t < numPicture:
try:
url = tmp + str(t)
result = requests.get(url, timeout=10)
print(url)
except error.HTTPError as e:
print('网络错误,请调整网络后重试')
t = t + 60
else:
dowmloadPicture(result.text, word)
t = t + 60
numPicture = numPicture + tm
print('任务完成')
2. 运行代码:python3 spider.py
会提示你输入的数量,结果如下:
3. 结果新建了两个文件夹,刘亦菲和刘德华。
4. 文件夹里的内容如下: