dirty web scraping szfdc huarun4

gistfile1.txt

用法：安装anaconda
python szfdc.py > hr4.txt

一次一栋，抓其他的要自己改改 urlz 链接

szfdc.py

from urllib.request import urlopen
from bs4 import BeautifulSoup
import re

urlz = "http://zjj.sz.gov.cn/ris/bol/szfdc/building.aspx?id=38063&presellid=49373"
htmlz = urlopen(urlz)
soupz = BeautifulSoup(htmlz, 'lxml')
all_links = soupz.find_all("a",href=re.compile('housedetail'))
# 默认只抓了前12个
# for link in all_links[:]:
for link in all_links[:12]:
    theurl = "http://zjj.sz.gov.cn/ris/bol/szfdc/" + link.get("href")
    #print (theurl)
    thehtml = urlopen(theurl)
    thesoup = BeautifulSoup(thehtml, 'lxml')
    tds = thesoup.find_all('td')
    mystr = "\t".join([tds[1].text.strip(),tds[11].text.strip(),tds[7].text.strip(),tds[15].text.strip(),tds[17].text.strip(),tds[19].text.strip(),tds[13].text.strip()])
    print(mystr)
print (urlz)