我正在尝试制作图片抓取工具,我首先在Google上尝试过,但是没有图片被抓取因此,我尝试使用Bing并成功了,但存在一些问题
我想删除bing.com/images/search中显示的所有图像(或某些页面)但实际上,它的作用很小。
[检查后,我发现图像链接存储在bing的'thumb'类中,所以我废弃了所有具有thumb类的链接,但是看起来还不够。
在查看源代码之后,仅发现实际上以.jpg结尾的thumb类链接
import requests
from bs4 import BeautifulSoup
import os
import random
from urllib.parse import urljoin
url = "https://www.bing.com"
search = input("enter the search term: ")
r = requests.get(url + "/images/search", params={"q":search})
soup = BeautifulSoup(r.content,"html.parser")
li = soup.find_all("a",class_="thumb")
# getting links from thumb class
links = [l.get("href") for l in li]
print("{0} results found with the search term: {1}".format(len(links), search))
choice = input("Do You Want To Extract The Images? Y or N ")
dir_name = "Result"
# Creating the Result named directory if it didn't existed
if os.path.isdir(dir_name) == False:
print("[+] Creating Directory Named '{0}'".format(dir_name))
os.mkdir(dir_name)
n = 1
if(choice == 'Y' or choice == 'y'):
for i in links:
req = requests.get(i)
#title = links[z].split("/")[-1]
#there were some issues with the default titles so I instead used names generated by
#random sequence
print("[+] Extracting Image #",n)
with open(("{0}/" + generateRandomSequence() + ".jpg").format(dir_name),"wb") as img:
img.write(req.content)
n += 1
#for generating random sequence
def generateRandomSequence():
seq = ""
letters = ["a","b","c","d","e","f","g","h","i","j","k","l","m","n","o","p","q","r","s","t","u","v","w","x","y","z",
"A","B","C","D","E","F","G","H","I","J","K","L","M","N","O","P","Q","R","S","T","U","V","W","X","Y","Z",
]
for i in range(0,5):
seq = seq + random.choice(letters) + str(random.randrange(1,1000))
return seq
这是给您的废料: