Python大批量搜索引擎图像爬虫工具详解

pip install icrawler

from icrawler.builtin import BaiduImageCrawler 
from icrawler.builtin import BingImageCrawler 
from icrawler.builtin import GoogleImageCrawler 
#需要爬虫的关键字
list_word = ['抽烟 行人','吸烟 行人','接电话 行人','打电话 行人', '玩手机 行人']
for word in list_word:
  #bing爬虫
  #保存路径
  bing_storage = {'root_dir': 'bing\\'+word}
  #从上到下依次是解析器线程数，下载线程数，还有上面设置的保存路径
  bing_crawler = BingImageCrawler(parser_threads=2,
                  downloader_threads=4,
                  storage=bing_storage)
  #开始爬虫，关键字+图片数量
  bing_crawler.crawl(keyword=word,
            max_num=2000)

  #百度爬虫
  # baidu_storage = {'root_dir': 'baidu\\' + word}
  # baidu_crawler = BaiduImageCrawler(parser_threads=2,
  #                  downloader_threads=4,
  #                  storage=baidu_storage)
  # baidu_crawler.crawl(keyword=word,
  #           max_num=2000)


  # google爬虫
  # google_storage = {'root_dir': '‘google\\' + word}
  # google_crawler = GoogleImageCrawler(parser_threads=4,
  #                  downloader_threads=4,
  #                  storage=google_storage)
  # google_crawler.crawl(keyword=word,
  #           max_num=2000)