webspider-zhilianzhaoping.py 文件源码

def get_links_from(job, city, page):
    '''''
    @job:????
    @city:???????
    @page????????
    @urls???????????????

    ****************?????????**********************
    ?????????
    '''
    urls=[]
    for i in range(page):
        url = "http://sou.zhaopin.com/jobs/searchresult.ashx?jl={}&kw={}&p={}".format(str(city),str(job),i)
        url = quote(url, safe=string.printable)
        info = get_content(url,headers)
        soup = BeautifulSoup(info,"lxml")#??????“lxml”
        link_urls = soup.select('td.zwmc a')
        for url in link_urls:
            urls.append(url.get('href'))
    return (urls)


#url = "http://s.yingjiesheng.com/result.jsp?keyword=%E6%95%B0%E6%8D%AE%E6%8C%96%E6%8E%98&city=217&start=0&period=0&sort=score&jobtype=1"
#get_links_from('??','????', 5)