webscrapping.py

# import urllib2 library 用作 query 網頁
import urllib2

# import Beautiful soup 用作 parse 回傳頁面的 html
from bs4 import BeautifulSoup

#import pandas to convert list to data frame
import pandas as pd

import csv

for pageNo in range(1,1103):
    locatefamily = "http://www.locatefamily.com/Street-Lists/Hong-Kong/index-" + str(pageNo) + ".html"
    page = urllib2.urlopen(locatefamily)
    soup = BeautifulSoup(page, "html.parser")
    
    right_tables=soup.findAll('table', class_='table')

    #Generate lists
    A=[]
    B=[]
    C=[]
    D=[]
    E=[]

    for table in right_tables:
        for body in table.findAll("tbody"):
            for row in body.findAll("tr"):
                cells = row.findAll('td')
                people = row.findAll('th')
                if len(cells)==3:
                    A.append(pageNo)
                    B.append(people[0].find(text=True))
                    C.append(cells[0])
                    D.append(cells[1].find(text=True))
                    E.append(cells[2].find(text=True))
                    
    df=pd.DataFrame(A,columns=['PageNo'])
    df['No']=B
    df['Name']=C
    df['Address']=D
    df['Telephone']=E

    pageNum = '{:04d}'.format(pageNo)
    
    df.to_csv('page'+str(pageNum)+'.csv', sep=',', encoding='utf-8')