import re
import requests
from urllib import error
from bs4 import BeautifulSoup
import os
num = 0
numPicture = 0
file = ''
List = []
def Find(url, A):
global List
print('Search for images, please wait.....')
t = 0
i = 1
s = 0
while t < 1000:
Url = url + str(t)
try:
Result = A.get(Url, timeout=7, allow_redirects=False)
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 recommend(url):
Re = []
try:
html = requests.get(url, allow_redirects=False)
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('key word:' + keyword + 'image,Start downloading pictures...')
for each in pic_url:
print('Start downloading pictures' + str(num + 1) + 'image,image url:' + str(each))
try:
if each is not None:
pic = requests.get(each, timeout=7)
else:
continue
except BaseException:
print('error')
continue
else:
string = file + r'\\' + keyword + '_' + str(num) + '.jpg'
fp = open(string, 'wb')
fp.write(pic.content)
fp.close()
num += 1
if num >= numPicture:
return
if __name__ == '__main__':
headers = {
'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
'Connection': 'keep-alive',
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101 Firefox/60.0',
'Upgrade-Insecure-Requests': '1'
}
A = requests.Session()
A.headers = headers
#NUM_IMAGES要爬取的图像数量
tm = int(input('NUM_IMAGES '))
numPicture = tm
line_list = []
#name.txt与main.py文件在同级目录下,txt里为要爬取的图像关键词
with open('./name.txt', encoding='utf-8') as file:
line_list = [k.strip() for k in file.readlines()] # 用 strip()移除末尾的空格
for word in line_list:
url = 'https://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=' + word + '&pn='
tot = Find(url, A)
Recommend = recommend(url) # 记录相关推荐
print('%sclass image have %d samples' % (word, tot))
file = word + 'output'
y = os.path.exists(file)
if y == 1:
print('create a new file')
file = word + 'output2'
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)
result = A.get(url, timeout=10, allow_redirects=False)
print(url)
except error.HTTPError as e:
print('erro')
t = t + 60
else:
dowmloadPicture(result.text, word)
t = t + 60
# numPicture = numPicture + tm
print('end')
爬虫之爬取图像篇
最新推荐文章于 2023-04-24 15:55:10 发布