python爬取51job中hr的邮箱

#encoding=utf8
import urllib2
import cookielib
import re
import lxml.html
from _ast import TryExcept
from warnings import catch_warnings

f = open('/root/Desktop/51-01.txt','a+')

def read(city):
    url = 'http://www.51job.com/'+city
    cj = cookielib.MozillaCookieJar()  
    cookie_support = urllib2.HTTPCookieProcessor(cj)  
    opener = urllib2.build_opener(cookie_support)  
    opener.addheaders = [('User-agent','Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20100101 Firefox/38.0 Iceweasel/38.3.0')]
    urllib2.install_opener(opener)
    response = urllib2.urlopen(url)
    http = response.read()
    rex = 'http://jobs.51job.com/hot/.*?html'
    value = re.findall(rex, http)
    for i in value:
        print i
        try:
            readpage(i)
        except:
            pass
        
def readpage(url):
    cj = cookielib.MozillaCookieJar()  
    cookie_support = urllib2.HTTPCookieProcessor(cj)  
    opener = urllib2.build_opener(cookie_support)  
    opener.addheaders = [('User-agent','Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20100101 Firefox/38.0 Iceweasel/38.3.0')]
    urllib2.install_opener(opener)
    html = urllib2.urlopen(url,timeout = 2).read()
    doc = lxml.html.fromstring(html)
    rex = r'[\w\.-][email protected](?:[A-Za-z0-9]+\.)+[A-Za-z]+'
    results = doc.xpath('//div[@class="tmsg inbox"]/div[@class="con_msg"]/div[@class="in"]/p/text()')
    for i in results:
        xx = re.compile(rex)
        for j in xx.findall(i):
            print j
            f.write(j+'\n')
            f.flush()
    

if __name__ == '__main__':
    city_list = ['zhangjiagang','zhanjiang','zhaoqing','zibo']
    for i in city_list:
        f.write(i+'\n')
        f.flush()
        try:
            read(i)
        except:
            pass
    f.flush()
    f.close()

city_list大家自己整理一下，只能帮你们到这里了。

 

转载于:https://my.oschina.net/passer007/blog/675156