1. 异步加载爬虫
对于静态页面爬虫很容易获取到站点的数据内容，然而静态页面需要全量加载站点的所有数据，对于网站的访问和带宽是巨大的挑战，对于高并发和大访问访问量的站点来说，需要使用AJAX相关的技术来实现异步加载，即根据需要来获取数据，以pexels网站为例，按F12，切换到Network的XHR标签，通过下拉菜单访问该站点，此时数据会以此加载，在XHR页面中会逐步增加访问的URL地址，点击查看其中一个URL地址，发现其URL的地址类似为:https://www.pexels.com/search/book/?page=3&seed=2018-02-22+05:21:39++0000&format=js&seed=2018-02-22 05:21:39 +0000,将其修改为https://www.pexels.com/search/book/?page=3，并修改page后面数的值发现可以访问到不同的页面内容，以此来构造需要访问的url站点内容。
2. 代码内容
#!/usr/bin/python
#_*_ coding:utf _*_
#author: HappyLau
#blog: https://www.cnblogs.com/cloudlab import os
import sys
import time
import os.path
import random
import requests
from lxml import etree reload(sys)
sys.setdefaultencoding('utf8') def get_jianshu(url):
'''
demo简书网站的获取信息
'''
headers = {"User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Firefox/52.0"}
try:
req = requests.get(url,headers=headers)
if req.status_code == 200:
return req.text.encode('utf8')
else:
return ''
except Exception as e:
print e def get_picture(url,download_dir):
'''
@params:获取url中的图片信息，并将其下载到download_dir目录中
@download_dir:图片下载的本地路径
'''
if not os.path.exists(download_dir):
os.mkdir(download_dir)
html = get_jianshu(url)
selector = etree.HTML(html)
for url in selector.xpath('//img[@class="photo-item__img"]/@src'):
picture_name = url.split("?")[0].split("/")[-1]
print "downloading picutre %s" % (picture_name)
with file(download_dir + picture_name,'wb') as f:
f.write(requests.get(url).content)
time.sleep(random.randint(1,3)) if __name__ == "__main__":
url_lists = ['https://www.pexels.com/search/book/?page={}'.format(i) for i in range(1,21)]
for url in url_lists:
get_picture(url,'/root/pexels')
3. 下载图片使用方式
上面使用requests.get().content的方式来实现下载图片的方法，还可以通过urllib.urlretrieve()方法来实现图片的下载功能，该函数的使用参数为:retrieve(self, url, filename=None, reporthook=None, data=None),其中url地址为需要访问的url路径，filename为本地存放图片的路径，修改代码内容如下：
#!/usr/bin/python
#_*_ coding:utf _*_
#author: HappyLau
#blog: https://www.cnblogs.com/cloudlab import os
import sys
import time
import os.path
import random
import requests
import urllib
from lxml import etree reload(sys)
sys.setdefaultencoding('utf8') def get_jianshu(url):
'''
demo简书网站的获取信息
'''
headers = {"User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Firefox/52.0"}
try:
req = requests.get(url,headers=headers)
if req.status_code == 200:
return req.text.encode('utf8')
else:
return ''
except Exception as e:
print e def get_picture(url,download_dir):
'''
@params:获取url中的图片信息，并将其下载到download_dir目录中
@download_dir:图片下载的本地路径
通过利用urllib模块中的urlretrieve()方法实现图片的下载功能
'''
if not os.path.exists(download_dir):
os.mkdir(download_dir)
html = get_jianshu(url)
selector = etree.HTML(html)
for url in selector.xpath('//img[@class="photo-item__img"]/@src'):
picture_name = download_dir + "/" + url.split("?")[0].split("/")[-1]
print "downloading picutre %s" % (picture_name)
urllib.urlretrieve(url,picture_name) #下载图片
time.sleep(random.randint(1,3)) if __name__ == "__main__":
url_lists = ['https://www.pexels.com/search/book/?page={}'.format(i) for i in range(1,21)]
for url in url_lists:
get_picture(url,'/root/pexels')