python网络爬虫_爬图片
1.安装 Beautifulsoup4
#解析返回的html与json数据
pip install Beautifulsoup4
使用 :
运行后输入要搜索的关键字
输入要下载的数量
输入需要保存的文件夹名称
#解析返回的html与json数据 ;jupyter noteBook
# !pip install Beautifulsoup4
##使用
# 运行后输入要搜索的关键字
# 输入要下载的数量
# 输入需要保存的文件夹名称
import re
import requests
from urllib import error
from bs4 import BeautifulSoup
import os
import cv2
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
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:
break
else:
List.append(pic_url)
t = t + 60
return s
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))
cap=cv2.VideoCapture(each)
ret=cap.isOpened()
if (ret):
ret,img=cap.read()
if ret:
img = cv2.resize(img, (150, 150), interpolation = cv2.INTER_AREA)
cv2.imwrite('./'+file+'/'+file+str(num + 1)+".jpg", img)
cap.release()
num += 1
if num >= numPicture:
return
if __name__ == '__main__': # 主函数入口
word = input("请输入搜索关键词: ")
#add = 'http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=%E5%BC%A0%E5%A4%A9%E7%88%B1&pn=120'
url = 'http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=' + word + '&pn='
tot = Find(url)
print('经过检测%s类图片共有%d张' % (word, tot))
numPicture = int(input('请输入想要下载的图片数量 '))
file = input('请建立一个存储图片的文件夹,输入文件夹名称即可')
y = os.path.exists(file)
if y == 1:
print('该文件已存在,请重新输入')
file = input('请建立一个存储图片的文件夹,)输入文件夹名称即可')
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
print('当前搜索结束,感谢使用')