Python爬取豆瓣指定书籍的短评
#!/usr/bin/python
# coding=utf-8
import re
import sys
import time
import random
import urllib
import urllib2
import MySQLdb
# 爬取豆瓣评论
class Douban:
# 构造函数
def __init__(self, url, name):
# 采集的地址
#self.url = /subject/26356948/comments/hot
self.url = url
# 存储的文件名
self.filename = str(name) + .txt
# 数据库配置
self.database = {
host: 127.0.0.1,
username: oot,
password: oot,
database: douban,
charset: utf8,
able: str(name),
}
# HTTP请求超时
self.http_timeout = 10
# 请求计数器
self.request_cou