import urllib.request
import bs4
import urllib.error
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36"}
def get_html(url):
request = urllib.request.Request(url, headers=headers)
response = urllib.request.urlopen(request)
html = response.read().decode("utf-8")
return html
j = 0
def html_parse(html):
global j
soup = bs4.BeautifulSoup(html, "lxml")
pic_lists = soup.find('ul', attrs={"class": "thumbnails"})
pic_list = pic_lists.find_all('li')
for pics in pic_list:
pic_url = pics.find('img')['src']
urllib.request.urlretrieve(pic_url, "D:\工作\python\网络爬虫开发实战\images\%s.jpg" % j)
j += 1
def main():
i = 1
while i < 4:
url = "https://www.dbmeinv.com/?pager_offset=" + str(i)
html = get_html(url)
html_parse(html)
i += 1
if __name__ == "__main__":
main()
爬虫实战3:爬取豆瓣妹子图片
最新推荐文章于 2021-05-31 19:21:27 发布