马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
本帖最后由 potatoking006 于 2021-4-12 21:02 编辑
运行前必须要改savaphoto() 里的保存路径。import urllib
import urllib.request
from bs4 import BeautifulSoup
import re
import time
def main():
baseurl=r"https://www.zhihu.com/question/325648700/answer/1366875354"
temp = gethtml(baseurl)
# print(temp)
# savaphoto(r"https://pic2.zhimg.com/50/v2-29b5b450b2c5f828195c359148099def_hd.jpg","1")
ImgUrlList = getImgUrlList(temp)
for i in range(len(ImgUrlList)):
print(ImgUrlList[i])
time.sleep(12)
savaphoto(ImgUrlList[i],"第一次壁纸"+str(i))
# # time.sleep(5)
# savaphoto("https://pic4.zhimg.com/50/v2-90a72927dc97d2ad5d748860158c6a0b_hd.jpg", "第一次壁纸" + str(1000))
def gethtml(baseUrl):
head = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.114 Safari/537.36"}
html = " "
request = urllib.request.Request(baseUrl,headers=head)
response = urllib.request.urlopen(request);
html = response.read().decode("utf-8")
return html
def getImgUrlList(html):
ImgUrlList = []
soup = BeautifulSoup(html,"html.parser")
findImgUrl=re.compile(r"src="(.*?.jpg)")
for item in soup.find_all("figure"):
item = str(item)
temp = re.findall(findImgUrl,item)[0]
ImgUrlList.append(temp)
# print(temp)
return ImgUrlList
def savaphoto(photoUrl,imgName):
head = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.114 Safari/537.36"}
request = urllib.request.Request(photoUrl,headers=head)
try:
reponse = urllib.request.urlopen(request)
my_img = reponse.read()
reponse.close()
##这里需要自己改路径名
with open(r"E:/spiderphoto/new/"+imgName+".jpg","wb") as f:
f.write(my_img)
except Exception:
print("访问出现错误")
finally:
print("正常爬取一张图片")
if __name__ == "__main__":
main()
print('mission success!!!')
time.sleep()方法建议设置的长一点,不然容易被反爬。
我用sleep (10)爬取到了99张图片。如果中途被断开连接,可以调整for 中 range的初始位置重新运行程序来达到继续爬壁纸的目的。
|