1. # coding=utf-8
  2. """根据搜索词下载百度图片"""
  3. import re
  4. import sys
  5. import urllib
  7. import requests
  10. def get_onepage_urls(onepageurl):
  11.     """获取单个翻页的所有图片的urls+当前翻页的下一翻页的url"""
  12.     if not onepageurl:
  13.         print(\'已到最后一页, 结束\')
  14.         return [], \'\'
  15.     try:
  16.         html = requests.get(onepageurl).text
  17.     except Exception as e:
  18.         print(e)
  19.         pic_urls = []
  20.         fanye_url = \'\'
  21.         return pic_urls, fanye_url
  22.     pic_urls = re.findall(\'"objURL":"(.*?)",\', html, re.S)
  23.     fanye_urls = re.findall(re.compile(r\'<a href="(.*)" class="n">下一页</a>\'), html, flags=0)
  24.     fanye_url = \'http://image.baidu.com\' + fanye_urls[0] if fanye_urls else \'\'
  25.     return pic_urls, fanye_url
  28. def down_pic(pic_urls):
  29.     """给出图片链接列表, 下载所有图片"""
  30.     for i, pic_url in enumerate(pic_urls):
  31.         try:
  32.             pic = requests.get(pic_url, timeout=15)
  33.             string = str(i + 1) + \'.jpg\'
  34.             with open(string, \'wb\') as f:
  35.                 f.write(pic.content)
  36.                 print(\'成功下载第%s张图片: %s\' % (str(i + 1), str(pic_url)))
  37.         except Exception as e:
  38.             print(\'下载第%s张图片时失败: %s\' % (str(i + 1), str(pic_url)))
  39.             print(e)
  40.             continue
  41.  
  42.  
  43. if __name__ == \'__main__\':
  44.     keyword = \'bus\'  # 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
  45.     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=\'
  46.     url_init = url_init_first + urllib.quote(keyword, safe=\'/\')
  47.     all_pic_urls = []
  48.     onepage_urls, fanye_url = get_onepage_urls(url_init)
  49.     all_pic_urls.extend(onepage_urls)
  51.     fanye_count = 0  # 累计翻页数
  52.     while 1:
  53.         onepage_urls, fanye_url = get_onepage_urls(fanye_url)
  54.         fanye_count += 1
  55.         print(\'第%s页\' % fanye_count)
  56.         if fanye_url == \'\' and onepage_urls == []:
  57.             break
  58.         all_pic_urls.extend(onepage_urls)
  60.     down_pic(list(set(all_pic_urls)))

 

版权声明：本文为zhoulixue原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://www.cnblogs.com/zhoulixue/p/8394959.html