Parsing #2 [i.cantonfair.org.cn]

i.cantonfair.org.cn.py

from sys import exit
from pprint import pprint

import lxml.html
import requests
import re

url = 'http://i.cantonfair.org.cn/en/ExpExhibitorList.aspx?k=glassware&page=1'
doc = requests.get(url)
root = lxml.html.fromstring(doc.text)

regexp_total_pages = re.compile(ur"Pages\s\d\/(\d+)")
text_total_pages = root.xpath('//*[@id="AspNetPager1"]/div[1]/text()')[0].strip()
total_pages = int(re.match(regexp_total_pages,text_total_pages).group(1))

all_links = list()

for i in range(1,total_pages + 1):
	url = "http://i.cantonfair.org.cn/en/ExpExhibitorList.aspx?k=glassware&page={page}".format(page=i)
	doc = requests.get(url)
	root = lxml.html.fromstring(doc.text)
	all_links.append(root.xpath('//*[@id="form1"]/div[*]/div[*]/h3/a/@href'))

pprint(all_links)