coding=utf-8
"""根据搜索词下载百度图片"""
import re
import urllib
import os
def get_onepage_urls(onepageurl):
"""获取单个翻页的所有图片的urls+当前翻页的下一翻页的url"""
try:
page = urllib.urlopen(onepageurl) # urllib.urlopen()方法用于打开一个URL地址
html = page.read() # read()方法用于读取URL上的数据
except Exception as e:
pic_urls = []
fanye_url = ''
return pic_urls, fanye_url
pic_urls = re.findall('"objURL":"(.*?)",', html, re.S)
fanye_urls = re.findall(re.compile(r'下一页'), html, flags=0)
fanye_url = 'http://image.baidu.com' + fanye_urls[0] if fanye_urls else ''
return pic_urls, fanye_url
Dir = os.path.join('E://', 'pic')
def down_pic(pic_urls):
if not os.path.exists(Dir):
os.makedirs(Dir)
"""给出图片链接列表, 下载所有图片"""
for i, pic_url in enumerate(pic_urls):
try:
urllib.urlretrieve(pic_url, os.path.join(Dir, '%s.jpg') % str(i + 1))
print('成功下载第%s张图片: %s' % (str(i + 1), str(pic_url)))
except Exception as e:
print('下载第%s张图片时失败: %s' % (str(i + 1), str(pic_url)))
print(e)
continue
if __name__ == '__main__':
keyword = '狗狗' # 关键词, 改为你想输入的词即可, 相当于在百度图片里搜索一样
url_init_first = r'http://image.baidu.com/search/flip?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=result&fr=&sf=1&fmq=1497491098685_R&pv=&ic=0&nc=1&z=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&ctd=1497491098685%5E00_1519X735&word='
url_init = url_init_first + urllib.quote(keyword, safe='/')
all_pic_urls = []
onepage_urls, fanye_url = get_onepage_urls(url_init)
all_pic_urls.extend(onepage_urls)
fanye_count = 0 # 累计翻页数
while 1:
onepage_urls, fanye_url = get_onepage_urls(fanye_url)
fanye_count += 1
print('第%s页' % fanye_count)
all_pic_urls.extend(onepage_urls)
if fanye_url == '' and onepage_urls == []:
print('已到最后一页, 开始下载图片：')
break
down_pic(all_pic_urls)
print '图片下载完毕'
Original: https://www.cnblogs.com/createboke/p/8359263.html
Author: CREATE_17
Title: python根据搜索词下载百度图片
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/714057/
转载文章受原作者版权保护。转载请注明原作者出处！