python多线程抓取天涯帖子内容示例

python多线程抓取天涯帖子内容示例

使用re, urllib, threading　多线程抓取天涯帖子内容，设置url为需抓取的天涯帖子的第一页，设置file_name为下载后的文件名

复制代码 代码如下:
#coding:utf-8

import urllib
import re
import threading
import os, time

class Down_Tianya(threading.Thread):
    """多线程下载"""
    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):
        """根据传入的url抓出各页内容，按页数做键存入字典"""
        html_content =urllib.urlopen(self.url).read()
        text_pattern = re.compile('时间：(.*?).*?.*?s*(.*?)', re.DOTALL)
        text = text_pattern.findall(html_content)
        text_join = ['rnrnrnrn'.join(item) for item in text]
        self.txt_dict[self.num] = text_join

 

def page(url):
    """根据第一页地址抓取总页数"""
    html_page = urllib.urlopen(url).read()
    page_pattern = re.compile(r'(d*)s*下页')
    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):
    """把字典内容按键（页数）写入文本，每个键值为每页内容的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('
', 'rn').replace('
', 'rn').replace(' ', '')
            tx_file.write(tx.strip()+'rn'*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 = []

    """根据页数构造urls进行多线程下载"""
    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)

    """检查下载完成后再进行写入"""
    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()

down_tianya.py

复制代码 代码如下:
#coding:utf-8

import urllib
import re
import threading
import os

class Down_Tianya(threading.Thread):
    """多线程下载"""
    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):
        """根据传入的url抓出各页内容，按页数做键存入字典"""
        html_content =urllib.urlopen(self.url).read()
        text_pattern = re.compile('时间：(.*?).*?.*?s*(.*?)', re.DOTALL)
        text = text_pattern.findall(html_content)
        text_join = ['rnrnrnrn'.join(item) for item in text]
        self.txt_dict[self.num] = text_join

 

def page(url):
    """根据第一页地址抓取总页数"""
    html_page = urllib.urlopen(url).read()
    page_pattern = re.compile(r'(d*)s*下页')
    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):
    """把字典内容按键（页数）写入文本，每个键值为每页内容的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('
', 'rn').replace('
', 'rn').replace(' ', '')
            tx_file.write(tx.strip()+'rn'*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 = []

    """根据页数构造urls进行多线程下载"""
    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)

    """检查下载完成后再进行写入"""
    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()