如何从网站上抓取图片？

Question

如何获取此站点的所有图像：http://www.theft-alerts.com 我们需要19页的图片。我们已经有了这个代码，但它还不起作用。我们要新地图上的图像。在

#!/usr/bin/python

import [urllib2][1]
from bs4 import BeautifulSoup
from urlparse  import urljoin

url = "http://www.theft-alerts.com/index-%d.html"
page = urllib2.urlopen(url).read()
soup = BeautifulSoup(page, "html.parser")

base = "http://www.theft-alerts.com"

images = [urljoin(base,a["href"]) for a in soup.select("td a[href^=images/]")]

for url in images:
    img = BeautifulSoup(urllib2.urlopen(url).read(),"lxml").find("img")["src"]
with open("myimages/{}".format(img), "w") as f:
    f.write(urllib2.urlopen("{}/{}".format(url.rsplit("/", 1)[0], img)).read())

Answer 1

您需要遍历每一页并提取图像，您可以一直循环，直到文本"Next"的锚点位于类resultnav的代码标记中：

import  requests

from bs4 import BeautifulSoup
from urlparse import urljoin

def get_pages(start):
    soup = BeautifulSoup(requests.get(start).content)
    images = [img["src"] for img in soup.select("div.itemspacingmodified a img")]
    yield  images
    nxt = soup.select("code.resultnav a")[-1]
    while True:
        soup = BeautifulSoup(requests.get(urljoin(url, nxt["href"])).content)
        nxt = soup.select("code.resultnav a")[-1]
        if nxt.text != "Next":
            break
        yield [img["src"] for img in soup.select("div.itemspacingmodified a img")]




url = "http://www.theft-alerts.com/"

for images in get_pages(url):
    print(images)

这给了你所有19页的图片。在