python 版本 3.5
依赖库:
selenium
beautifulsoap4
lxml
requests
使用selenium的原因是
requests库 在实际操作的时候,发现请求返回的内容里面并没有图片的链接:
<p> <img src="//img.jandan.net/img/blank.gif" onload="jandan_load_img(this)"/> <span class="img-hash">6fadiP6jpEOinbyOjDMf5F1MT01mhMHpB0oC562st3bqZwhPR+OhO+YvbyrNqKyKMmBNGSDh7Gk0I+B+zcKmrgCm3n1M0bXlNjhOjdDps9/hCO039Uo2+w</span> </p>
而在chrome中使用F12去可以看到图片链接,看来这个页面需要调用js方法才会返回图片的url
那我们 只好使用 Selenium+Phantomjs 来实现需求
第一步
导入依赖库:
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import requests
from bs4 import BeautifulSoup
第二步
使用Selenium+Phantomjs爬取完整的页面源码,用bs解析网页,定位元素
path='D:/jd_image/'
urls = ["http://jandan.net/ooxx/page-{}#comments".format(str(i)) for i in range(1, 50)]
img_url=[]
driver = webdriver.PhantomJS(executable_path=r'D:\phantomjs-2.1.1-windows\bin\phantomjs.exe')
for url in urls:
driver.get(url)
data = driver.page_source
soup = BeautifulSoup(data, "lxml") #解析网页
images = soup.select("a.view_img_link") #定位元素
for i in images:
z=i.get('href')
if str('gif') in str(z):
pass
else:
http_url = "http:" + z
img_url.append(http_url)
#print("http:%s" % z)
第三步
下载图片
for j in img_url:
r=requests.get(j)
print('正在下载 %s......' % j)
with open(path+j[-15:],'wb')as jpg:
jpg.write(r.content)
完整代码:
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import requests
from bs4 import BeautifulSoup
path='D:/jd_image/'
urls = ["http://jandan.net/ooxx/page-{}#comments".format(str(i)) for i in range(1, 50)]
img_url=[]
driver = webdriver.PhantomJS(executable_path=r'D:\phantomjs-2.1.1-windows\bin\phantomjs.exe')
for url in urls:
driver.get(url)
data = driver.page_source
soup = BeautifulSoup(data, "lxml")
images = soup.select("a.view_img_link")
for i in images:
z=i.get('href')
if str('gif') in str(z):
pass
else:
http_url = "http:" + z
img_url.append(http_url)
#print("http:%s" % z)
for j in img_url:
r=requests.get(j)
print('正在下载 %s......' % j)
with open(path+j[-15:],'wb')as jpg:
jpg.write(r.content)