舆情分析项目-重庆公交坠江原因

import json
import requests
import pymysql
import time as timeimport
from mylog import Logger

logger1 = Logger(logfile=‘log1.log‘, logname="log1", logformat=1).getlog()  # 使用自定义日志对象

# 连接数据库
connect = pymysql.Connect(
    host=‘localhost‘,
    port=3306,
    user=‘root‘,
    passwd=‘root‘,
    db=‘analyze‘,
    charset=‘utf8‘
)
# 获取游标
cursor = connect.cursor()

# 创建数据库语句


for page_num in range(1, 6001):  # 从1采集到6000条评论

    if page_num % 50 == 0:  # 每采集50条数据，休息2秒
        timeimport.sleep(2)

    url = "http://comment5.news.sina.com.cn/page/info?version=1&format=js&channel=gn&newsid=comos-hnfikve6671738&group=0&compress=0&ie=utf8&oe=utf8&page=" + str(
        page_num) + "&page_size=1&jsvar=loader_1541133929419_28637561"
    # url = "http://comment5.news.sina.com.cn/page/info?version=1&format=js&channel=gn&newsid=comos-hnfikve6671738&group=0&compress=0&ie=gbk&oe=gbk&page=1&page_size=2&jsvar=loader_1541133929419_28637561"

    headers = {
        ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36‘
    }
    try:  # 尝试采集
        # 发出请求获取响应
        response = requests.get(url, headers=headers)
        data_str = response.content.decode(‘unicode_escape‘)
        # 排除干扰字符串
        data_str = data_str.lstrip("var loader_1541133929419_28637561=")
        # print(data_str)
        # str转字典
        data_dict = json.loads(data_str)
        print(type(data_dict))
        # 获取每次响应中的所有评论
        all_remarks = data_dict[‘result‘][‘cmntlist‘]
        print(len(all_remarks))

        i = 0
        for c in all_remarks:  # 遍历每次响应中的评论，并存入mysql
            i += 1
            print(i, "*" * 100)
            nick = c["nick"]  # 昵称
            content = c["content"]  # 评论
            agree = int(c["agree"])  # 收到点赞
            area = c["area"]  # 地区
            ip = c["ip"]  # 源ip
            time = c["time"]  # 评论发布时间
            profile_img = c["profile_img"]  # 头像

            print(nick)
            print(content)
            print(agree)
            print(ip)
            print(time)
            print(profile_img)

            # sql操作
            # 增加数据操作
            sql_1 = "insert into all_remarks(nick, content, agree, area, ip, time, profile_img) values(%s,%s,%s,%s,%s,%s,%s)"
            data = (nick, content, agree, area, ip, time, profile_img)
            cursor.execute(sql_1, data)  # 生成增加sql语句
            connect.commit()  # 确认永久执行增加
    except Exception as e:  # 采集异常处理
        my_e = str(e) + " ==> " + str(url)
        logger1.warning(my_e)  # 定义调试日志内容
        # print(my_e)
        continue  # 忽视异常，进行后面的采集

# 开发一个日志系统， 既要把日志输出到控制台， 还要写入日志文件
import logging

# 用字典保存输出格式
format_dict = {
    1: logging.Formatter(‘%(asctime)s - %(name)s - %(filename)s - %(levelname)s - %(message)s‘),
    2: logging.Formatter(‘%(asctime)s - %(name)s - %(levelname)s - %(message)s‘),
    3: logging.Formatter(‘%(asctime)s - %(name)s - %(levelname)s - %(message)s‘),
    4: logging.Formatter(‘%(asctime)s - %(name)s - %(levelname)s - %(message)s‘),
    5: logging.Formatter(‘%(asctime)s - %(name)s - %(levelname)s - %(message)s‘)
}


class Logger():
    def __init__(self, logfile, logname, logformat):
        ‘‘‘
           指定保存日志的文件路径，日志级别，以及调用文件
           将日志存入到指定的文件中
        ‘‘‘

        # 创建一个logger
        self.logger = logging.getLogger(logname)
        self.logger.setLevel(logging.DEBUG)

        # 创建一个handler，用于写入日志文件
        fh = logging.FileHandler(logfile)
        fh.setLevel(logging.DEBUG)

        # 再创建一个handler，用于输出到控制台
        ch = logging.StreamHandler()
        ch.setLevel(logging.DEBUG)

        # 定义handler的输出格式
        # formatter = logging.Formatter(‘%(asctime)s - %(name)s - %(levelname)s - %(message)s‘)
        formatter = format_dict[int(logformat)]
        fh.setFormatter(formatter)
        ch.setFormatter(formatter)

        # 给logger添加handler
        self.logger.addHandler(fh)
        self.logger.addHandler(ch)

    def getlog(self):
        return self.logger


if __name__ == ‘__main__‘:
    logger1 = Logger(logfile=‘log1.txt‘, logname="fox1", logformat=1).getlog()
    logger1.debug(‘i am debug‘)
    logger1.info(‘i am info‘)
    logger1.warning(‘i am warning‘)
    logger2 = Logger(logfile=‘log2.txt‘, logname="fox2", logformat=2).getlog()
    logger2.debug(‘i am debug2‘)
    logger2.info(‘i am info2‘)
    logger2.warning(‘i am warning2‘)

/*
Navicat MySQL Data Transfer

Source Server         : win7_local
Source Server Version : 50717
Source Host           : localhost:3306
Source Database       : analyze

Target Server Type    : MYSQL
Target Server Version : 50717
File Encoding         : 65001

Date: 2018-11-02 17:12:24
*/

SET FOREIGN_KEY_CHECKS=0;

-- ----------------------------
-- Table structure for all_remarks
-- ----------------------------
DROP TABLE IF EXISTS `all_remarks`;
CREATE TABLE `all_remarks` (
  `id` int(11) unsigned NOT NULL AUTO_INCREMENT,
  `nick` varchar(255) DEFAULT NULL,
  `content` text,
  `agree` int(10) DEFAULT NULL,
  `area` varchar(100) DEFAULT NULL,
  `ip` varchar(20) DEFAULT NULL,
  `time` datetime DEFAULT NULL ON UPDATE CURRENT_TIMESTAMP,
  `profile_img` varchar(255) DEFAULT NULL,
  PRIMARY KEY (`id`)
) ENGINE=InnoDB AUTO_INCREMENT=1 DEFAULT CHARSET=utf8;