<p>我有一个代码写的网站报废,可能会帮助你。
基本上,您需要做的是在web页面上单击gotohtml并尝试找到您要查找的表的标记,并使用模块(我正在使用beautifulsoup)提取信息。我正在创建一个json,因为我需要将它存储到mongodb中,您可以创建表。在</p>
<pre><code>#! /usr/bin/python
import sys
import requests
import re
from BeautifulSoup import BeautifulSoup
import pymongo
def req_and_parsing():
url2 = 'http://businfo.dimts.in/businfo/Bus_info/EtaByRoute.aspx?ID='
list1 = ['534UP','534DOWN']
for Route in list1:
final_url = url2 + Route
#r = requests.get(final_url)
#parsing_file(r.text,Route)
outdict = []
outdict = [parsing_file( requests.get(url2+Route).text,Route) for Route in list1 ]
print outdict
conn = f_connection()
for i in range(len(outdict)):
insert_records(conn,outdict[i])
def parsing_file(txt,Route):
soup = BeautifulSoup(txt)
table = soup.findAll("table",{"id" : "ctl00_ContentPlaceHolder1_GridView2"})
#trtags = table[0].findAll('tr')
tdlist = []
trtddict = {}
"""
for trtag in trtags:
print 'print trtag- ' , trtag.text
tdtags = trtag.findAll('td')
for tdtag in tdtags:
print tdtag.text
"""
divtags = soup.findAll("span",{"id":"ctl00_ContentPlaceHolder1_ErrorLabel"})
for divtag in divtags:
for divtag in divtags:
print "div tag - " , divtag.text
if divtag.text == "Currently no bus is running on this route" or "This is not a cluster (orange bus) route":
print "Page not displayed Errored with below meeeage for Route-", Route," , " , divtag.text
sys.exit()
trtags = table[0].findAll('tr')
for trtag in trtags:
tdtags = trtag.findAll('td')
if len(tdtags) == 2:
trtddict[tdtags[0].text] = sub_colon(tdtags[1].text)
return trtddict
def sub_colon(tag_str):
return re.sub(';',',',tag_str)
def f_connection():
try:
conn=pymongo.MongoClient()
print "Connected successfully!!!"
except pymongo.errors.ConnectionFailure, e:
print "Could not connect to MongoDB: %s" % e
return conn
def insert_records(conn,stop_dict):
db = conn.test
print db.collection_names()
mycoll = db.stopsETA
mycoll.insert(stop_dict)
if __name__ == "__main__":
req_and_parsing()
</code></pre>