XPath提取内容
//定位根节点
/ 往下层寻找
提取文本内容:/text()
提取属性内容 : /@XXXX
常规匹配
#-*-coding:utf8-*-
from lxml import etree
html = '''
<!DOCTYPE html>
<html>
<head lang="en">
<meta charset="UTF-8">
<title>测试-常规用法</title>
</head>
<body>
<div id="content">
<ul id="useful">
<li>这是第一条信息</li>
<li>这是第二条信息</li>
<li>这是第三条信息</li>
</ul>
<ul id="useless">
<li>不需要的信息1</li>
<li>不需要的信息2</li>
<li>不需要的信息3</li>
</ul>
<div id="url">
<a href="http://jikexueyuan.com">极客学院</a>
<a href="http://jikexueyuan.com/course/" title="极客学院课程库">点我打开课程库</a>
</div>
</div>
</body>
</html>
'''
selector = etree.HTML(html)
#提取文本
content = selector.xpath('//ul[@id="useful"]/li/text()')
for each in content:
print each
#提取属性
link = selector.xpath('//a/@href')
for each in link:
print each
title = selector.xpath('//a/@title')
print title[0]
特殊匹配
#-*-coding:utf8-*-
from lxml import etree
html1 = '''
<!DOCTYPE html>
<html>
<head lang="en">
<meta charset="UTF-8">
<title></title>
</head>
<body>
<div id="test-1">需要的内容1</div>
<div id="test-2">需要的内容2</div>
<div id="testfault">需要的内容3</div>
</body>
</html>
'''
html2 = '''
<!DOCTYPE html>
<html>
<head lang="en">
<meta charset="UTF-8">
<title></title>
</head>
<body>
<div id="test3">
我左青龙,
<span id="tiger">
右白虎,
<ul>上朱雀,
<li>下玄武。</li>
</ul>
老牛在当中,
</span>
龙头在胸口。
</div>
</body>
</html>
'''
selector = etree.HTML(html1)
content = selector.xpath('//div[starts-with(@id,"test")]/text()')
for each in content:
print each
# selector = etree.HTML(html2)
# content_1 = selector.xpath('//div[@id="test3"]/text()')
# for each in content_1:
# print each
#
#
# data = selector.xpath('//div[@id="test3"]')[0]
# info = data.xpath('string(.)')
# content_2 = info.replace('\n','').replace(' ','')
# print content_2
单线程与多线程耗时比较
#-*-coding:utf8-*-
from multiprocessing.dummy import Pool as ThreadPool
import requests
import time
def getsource(url):
html = requests.get(url)
urls = []
for i in range(1,21):
newpage = 'http://tieba.baidu.com/p/3522395718?pn=' + str(i)
urls.append(newpage)
time1 = time.time()
for i in urls:
print i
getsource(i)
time2 = time.time()
print u'单线程耗时:' + str(time2-time1)
pool = ThreadPool(4)
time3 = time.time()
results = pool.map(getsource, urls)
pool.close()
pool.join()
time4 = time.time()
print u'并行耗时:' + str(time4-time3)
多线程爬取百度贴吧
#-*-coding:utf8-*-
from lxml import etree
from multiprocessing.dummy import Pool as ThreadPool
import requests
import json
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
'''重新运行之前请删除content.txt,因为文件操作使用追加方式,会导致内容太多。'''
def towrite(contentdict):
f.writelines(u'回帖时间:' + str(contentdict['topic_reply_time']) + '\n')
f.writelines(u'回帖内容:' + unicode(contentdict['topic_reply_content']) + '\n')
f.writelines(u'回帖人:' + contentdict['user_name'] + '\n\n')
def spider(url):
html = requests.get(url)
selector = etree.HTML(html.text)
content_field = selector.xpath('//div[@class="l_post j_l_post l_post_bright "]')
print content_field
item = {}
for each in content_field:
reply_info = json.loads(each.xpath('@data-field')[0].replace('"', ''))
author = reply_info['author']['user_name']
content = each.xpath('div[@class="d_post_content_main"]/div/cc/div[@class="d_post_content j_d_post_content clearfix"]/text()')[0]
reply_time = reply_info['content']['date']
print content
print reply_time
print author
item['user_name'] = author
item['topic_reply_content'] = content
item['topic_reply_time'] = reply_time
towrite(item)
if __name__ == '__main__':
pool = ThreadPool(4)
f = open('content.txt', 'a')
page = []
for i in range(1, 21):
newpage = 'http://tieba.baidu.com/p/3522395718?pn=' + str(i)
page.append(newpage)
results = pool.map(spider, page)
pool.close()
pool.join()
f.close()
1、" 在html中表示英语中的双引号,如
<input id="txt" type="text" value=""好感动"">
你看下效果就知道了,主要为了区分语法上的引号
转载于:https://blog.51cto.com/tianxingzhe/1726602