首页 > 代码库 > 爬取知名社区技术文章_pipelines_4

爬取知名社区技术文章_pipelines_4

获取字段的存储处理和获取普通的路径

#!/usr/bin/python3
# -*- coding: utf-8 -*-

import pymysql
import gevent
import pymysql
from gevent import monkey
from scrapy.pipelines.images import ImagesPipeline
from twisted.enterprise import adbapi
import pymysql.cursors


class JobboleImagerPipeline(ImagesPipeline):
    """
    获得图片下载路径
    """
    def item_completed(self, results, item, info):
        if ‘img_url‘ in item:
            for key, value in results:
                # print(key)
                img_path = value[‘path‘]
                # print(value[‘path‘])
                item[‘img_path‘] = img_path
        return item
        

# class SqlSave(object):
#     """常规同步方式存入数据库"""
#     def __init__(self):
#         SQL_DBA = {
#             ‘host‘: ‘localhost‘,
#             ‘db‘: ‘jobole‘,
#             ‘user‘: ‘root‘,
#             ‘password‘: ‘jiayuan95814‘,
#             ‘use_unicode‘: True,
#             ‘charset‘: ‘utf8‘
#         }
#         self.conn = pymysql.connect(**SQL_DBA)
#         self.cursor = self.conn.cursor()
#
#     def process_item(self, item, spider):
#         sql = self.get_sql(item)
#         print(sql)
#         self.cursor.execute(sql)
#         self.conn.commit()
#
#         return item
#
#     def get_sql(self, item):
#         sql = """insert into article(cont_id, cont_url, title, publish_time, cont, img_url, img_path, like_num, collection_num, comment_num) value (‘%s‘,‘%s‘,‘%s‘,‘%s‘,‘%s‘,‘%s‘,‘%s‘, %d, %d, %d)
#         """ % (item[‘cont_id‘], item[‘cont_url‘],item[‘title‘],item[‘publish_time‘],item[‘cont‘],item[‘img_url‘][0],item[‘img_path‘],item[‘link_num‘],item[‘collection_num‘],item[‘comment_num‘],)
#         return sql


class SqlSave(object):
    """
    协程方式向数据库插入数据
    """
    
    def __init__(self):
        # 初始数据库连接和参数,SQL_DBA可写在setting中,通过 获取在settings.py中设置的SQL_DBA字典
        # @classmethod
        # def from_settings(cls, settings):
        #     sql_dba = settings[SQL_DBA]
        #     return cls(cls,sql_dba)           需要__init__中新添个参数接收这个值
        SQL_DBA = {
            ‘host‘: ‘localhost‘,
            ‘db‘: ‘jobole‘,
            ‘user‘: ‘root‘,
            ‘password‘: ‘jiayuan95814‘,
            ‘use_unicode‘: True,
            ‘charset‘: ‘utf8‘
        }
        self.conn = pymysql.connect(**SQL_DBA)
        self.cursor = self.conn.cursor()
    
    def process_item(self, item, spider):
        sql = self.__get_sql(item)
        # 协程方式对数据库插入操作
        gevent.joinall([
            gevent.spawn(self.__go_sql, self.cursor, self.conn, sql, item),
        ])
        return item
    
    def __go_sql(self, cursor, conn, sql, item):
        try:
            # 数据库插入操作
            cursor.execute(sql,
                           (item[‘cont_id‘], item[‘cont_url‘], item[‘title‘], item[‘publish_time‘],
                            item[‘cont‘], item[‘img_url‘][0], item[‘img_path‘], item[‘link_num‘],
                            item[‘collection_num‘], item[‘comment_num‘]))
            conn.commit()
        except Exception as e:
            print(e)
    
    def __get_sql(self, item):
        # 生成sql语句
        sql = """insert into
                  article(cont_id, cont_url, title, publish_time,
                  cont, img_url, img_path, like_num,
                  collection_num, comment_num)
                value
                  (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)"""
        return sql

  

爬取知名社区技术文章_pipelines_4