import urllib
import re
import threading
import os, time

class Down_Tianya(threading.Thread):
    """多線程下載"""
    def __init__(self, url, num, dt):
        threading.Thread.__init__(self)
        self.url = url
        self.num = num
        self.txt_dict = dt

    def run(self):
        print 'downling from %s' % self.url
        self.down_text()

    def down_text(self):
        """根據(jù)傳入的url抓出各頁(yè)內(nèi)容，按頁(yè)數(shù)做鍵存入字典"""
        html_content =urllib.urlopen(self.url).read()
        text_pattern = re.compile('<span>時(shí)間：(.*?)</span>.*?<!-- <div class="host-ico">樓主</div> -->.*?<div class="bbs-content.*?>\s*(.*?)</div>', re.DOTALL)
        text = text_pattern.findall(html_content)
        text_join = ['\r\n\r\n\r\n\r\n'.join(item) for item in text]
        self.txt_dict[self.num] = text_join

def page(url):
    """根據(jù)第一頁(yè)地址抓取總頁(yè)數(shù)"""
    html_page = urllib.urlopen(url).read()
    page_pattern = re.compile(r'<a href="\S*?">(\d*)</a>\s*<a href="\S*?" class="\S*?">下頁(yè)</a>')
    page_result = page_pattern.search(html_page)
    if page_result:
        page_num = int(page_result.group(1))
        return page_num

def write_text(dict, fn):
    """把字典內(nèi)容按鍵（頁(yè)數(shù)）寫(xiě)入文本，每個(gè)鍵值為每頁(yè)內(nèi)容的list列表"""
    tx_file = open(fn, 'w+')
    pn = len(dict)
    for i in range(1, pn+1):
        tx_list = dict[i]
        for tx in tx_list:
            tx = tx.replace('<br>', '\r\n').replace('<br />', '\r\n').replace('&nbsp;', '')
            tx_file.write(tx.strip()+'\r\n'*4)
    tx_file.close()

def main():
    url = 'http://bbs.tianya.cn/post-16-996521-1.shtml'
    file_name ='abc.txt'
    my_page = page(url)
    my_dict = {}

    print 'page num is : %s' % my_page

    threads = []

    """根據(jù)頁(yè)數(shù)構(gòu)造urls進(jìn)行多線程下載"""
    for num in range(1, my_page+1):
        myurl = '%s%s.shtml' % (url[:-7], num)
        downlist = Down_Tianya(myurl, num, my_dict)
        downlist.start()
        threads.append(downlist)

    """檢查下載完成后再進(jìn)行寫(xiě)入"""
    for t in threads:
        t.join()

    write_text(my_dict, file_name)

    print 'All download finished. Save file at directory: %s' % os.getcwd()

if __name__ == '__main__':
    main()

import urllib
import re
import threading
import os

class Down_Tianya(threading.Thread):
    """多線程下載"""
    def __init__(self, url, num, dt):
        threading.Thread.__init__(self)
        self.url = url
        self.num = num
        self.txt_dict = dt

    def run(self):
        print 'downling from %s' % self.url
        self.down_text()

    def down_text(self):
        """根據(jù)傳入的url抓出各頁(yè)內(nèi)容，按頁(yè)數(shù)做鍵存入字典"""
        html_content =urllib.urlopen(self.url).read()
        text_pattern = re.compile('<div class="atl-item".*?<span>時(shí)間：(.*?)</span>.*?<!-- <div class="host-ico">樓主</div> -->.*?<div class="bbs-content.*?>\s*(.*?)</div>', re.DOTALL)
        text = text_pattern.findall(html_content)
        text_join = ['\r\n\r\n\r\n\r\n'.join(item) for item in text]
        self.txt_dict[self.num] = text_join

def page(url):
    """根據(jù)第一頁(yè)地址抓取總頁(yè)數(shù)"""
    html_page = urllib.urlopen(url).read()
    page_pattern = re.compile(r'<a href="\S*?">(\d*)</a>\s*<a href="\S*?" class="\S*?">下頁(yè)</a>')
    page_result = page_pattern.search(html_page)
    if page_result:
        page_num = int(page_result.group(1))
        return page_num

def write_text(dict, fn):
    """把字典內(nèi)容按鍵（頁(yè)數(shù)）寫(xiě)入文本，每個(gè)鍵值為每頁(yè)內(nèi)容的list列表"""
    tx_file = open(fn, 'w+')
    pn = len(dict)
    for i in range(1, pn+1):
        tx_list = dict[i]
        for tx in tx_list:
            tx = tx.replace('<br>', '\r\n').replace('<br />', '\r\n').replace('&nbsp;', '')
            tx_file.write(tx.strip()+'\r\n'*4)
    tx_file.close()

def main():
    url = 'http://bbs.tianya.cn/post-16-996521-1.shtml'
    file_name ='abc.txt'
    my_page = page(url)
    my_dict = {}

    print 'page num is : %s' % my_page

    threads = []

    """根據(jù)頁(yè)數(shù)構(gòu)造urls進(jìn)行多線程下載"""
    for num in range(1, my_page+1):
        myurl = '%s%s.shtml' % (url[:-7], num)
        downlist = Down_Tianya(myurl, num, my_dict)
        downlist.start()
        threads.append(downlist)

    """檢查下載完成后再進(jìn)行寫(xiě)入"""
    for t in threads:
        t.join()

    write_text(my_dict, file_name)

    print 'All download finished. Save file at directory: %s' % os.getcwd()

if __name__ == '__main__':
    main()