网页爬虫 - Python爬虫运行内存占用过高导致电脑停止响应
各位好，我写了1个非常简单的爬虫去爬取51job里的招聘信息。从下面的链接里提取出每个招聘岗位的链接（一共50个链接）
http://search.51job.com/jobse...
再根据每个招聘岗位的url为每个岗位生成一个id，并且爬取每个岗位链接中的标题。最后把生成的信息打印到屏幕上。每次运行时内存占用率都会持续上升，最后导致电脑停止响应。代码非常简单，但是找不到哪里有问题。。我的环境是Ubuntu16.04,Python3.5,Pycharm.
尝试了下不用Pycharm直接运行还是不行，只输出了十几条信息后就停了。运行的时候一开始cpu很高，内存持续增长到2g多，电脑基本停止响应，用手机拍了一个图。过了几分钟后，cpu使用率掉下来了，但是内存占用还是80%左右。
import requests
from lxml import etree
import re
headers = {"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
"Accept-Encoding": "gzip, deflate",
"Accept-Language": "en-US,en;q=0.5",
"Connection": "keep-alive",
"Host": "jobs.51job.com",
"Upgrade-Insecure-Requests": "1",
"User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:52.0) Gecko/20100101 Firefox/52.0"}
def generate_info(url):
html = requests.get(url, headers=headers)
html.encoding = 'GBK'
select = etree.HTML(html.text.encode('utf-8'))
job_id = re.sub('[^0-9]', '', url)
job_title=select.xpath('/html/body//h1/text()')
print(job_id,job_title)
sum_page='http://search.51job.com/jobsearch/search_result.php?fromJs=1&jobarea=070200%2C00&district=000000&funtype=0000&industrytype=00&issuedate=9&providesalary=06%2C07%2C08%2C09%2C10&keywordtype=2&curr_page=1&lang=c&stype=1&postchannel=0000&workyear=99&cotype=99°reefrom=99&jobterm=99&companysize=99&lonlat=0%2C0&radius=-1&ord_field=0&list_type=0&dibiaoid=0&confirmdate=9'
sum_html=requests.get(sum_page)
sum_select=etree.HTML(sum_html.text.encode('utf-8'))
urls= sum_select.xpath('//*[@id="resultList"]/p/p/span/a/@href')
for url in urls:
generate_info(url)
