9.python爬虫--pyspider

pyspider简介

PySpider：一个国人编写的强大的网络爬虫系统并带有强大的WebUI。采用Python语言编写，分布式架构，支持多种数据库后端，强大的WebUI支持脚本编辑器，任务监视器，项目管理器以及结果查看器。在线示例：http://demo.pyspider .org/，学习教程：http://www.pyspider.cn/page/1.html

项目需求:

爬去 http://www.adquan.com/ 上面的文章供公司内部学习

简单实现，初步版（命名规范忽略）：

# -*- coding: utf-8 -*-
#__author:jiangjing
#date:2018/2/2
# !/usr/bin/env python
# -*- encoding: utf-8 -*-
# Created on 2017-12-07 13:40:43
# Project: adquan

from pyspider.libs.base_handler import *
import os
import urlparse
import datetime
import re
import requests
import uuid

UPLOAD_IMAGE_URL = "http://10.32.64.194:8233/api/NoLogin/UploadImage"       #上传图片至目标服务器
ADD_WEIBO_ARTICLE_URL = "http://10.32.64.194:8233/api/NoLogin/AddDraft"     #把当前文章添加到草稿
WEIBO_IMAGE_URL = "/upload/image"                                               #地址拼接用
PLAY_VIDEO_URL = "http://10.32.64.196:10001/hls/video/catch"                         #播放视频的地址
IMAGE_DIR_PATH = "/var/hls/image/catch"                                         #图片存放地址
VIDEO_DIR_PATH = "/var/hls/video/catch"                                         #视频存放地址

class Handler(BaseHandler):
    crawl_config = {
    }

    def __init__(self):
        self.deal = Deal()

    @every(minutes=24 * 60 * 3)
    def on_start(self):
        self.crawl('http://www.adquan.com', callback=self.index_page)

    @config(age=100 * 24 * 60 * 60)
    def index_page(self, response):
        for each in response.doc('.work_list_left .w_l_inner_img a').items():
            self.crawl(each.attr.href, callback=self.detail_page)

    @config(priority=2)
    def detail_page(self, response):
        today_str = datetime.date.today().strftime("%Y-%m-%d")
        # 抓取封面
        cover_guid = ''
        for img in response.doc('.con_pic_title img').items():
            url = img.attr.src
            if url:
                image_path = self.deal.getImageDirPath()
                extension = self.deal.getExtension(url)
                guid = str(uuid.uuid1()).replace('-', '')
                file_name = "origin_" + guid + '.' + extension
                file_path = image_path + '/' + file_name
                content = requests.get(url).content
                self.deal.saveImg(content, file_path)
                self.upload_image_to_weibo(file_path, guid, file_name)
                cover_guid = guid

        # 爬取图片
        for img in response.doc('.con_Text img').items():
            url = img.attr.src
            if url:
                extension = self.deal.getExtension(url)
                guid = str(uuid.uuid1()).replace('-', '')
                file_name = "origin_" + guid + '.' + extension
                self.crawl(img.attr.src, callback=self.save_img, save={'file_name': file_name, 'guid': guid})
                img.attr.src = '%s/%s/%s' % (WEIBO_IMAGE_URL, datetime.date.today().strftime("%Y%m%d"), file_name)
        # 抓取视频
        for video in response.doc('.con_Text iframe').items():
            width = video.attr.width
            if not width:
                width = 600
            iframe_url = str(video.attr('data-src')).strip()
            if not video.attr('data-src'):
                iframe_url = str(video.attr.src).strip()
            if not iframe_url:
                continue
            ret = urlparse.urlparse(iframe_url)
            vids = re.findall('vid=(\d|\w*)&?', ret.query)
            if not vids or not vids[0].strip():
                logger.error("get video id failed, url:%s" % (url))
                continue
            guid = str(uuid.uuid1()).replace('-', '')
            play_url = '%s/%s/%s.mp4' % (PLAY_VIDEO_URL, today_str, guid)
            cover_img= '%s/%s/%s.jpg' % (PLAY_VIDEO_URL, today_str, guid)
            video.replaceWith('<video controls="1" src=%s width=%s poster=%s></video>' % (play_url, str(width), cover_img))
            video.attr.poster = cover_img
            self.download_video(vids[0].strip(), guid)
        if response.doc('.text_title').text() != '':
            html_content = response.doc('.con_Text').html()
            text_content = self.deal.filterTag(html_content)
            self.add_article_to_weibo(response.doc('.text_title').text(), html_content , text_content, 2,
                                      cover_guid)

    def add_article_to_weibo(self, title, content, contentText, articleType, picguid):
        data = {'title': title, "content": content, "contentText": contentText, "articleType": articleType,
                "picguid": picguid}
        response = requests.post(ADD_WEIBO_ARTICLE_URL, data=data)
        return {
            "add_article_to_weibo": response.text
        }

    def download_video(self, vid, guid):
        data = {
            "otype": "xml",
            "platform": 11,
            "format": 2,
            "vid": vid,
            "filename": "1.mp4",
            "appver": '3.2.19.333'
        }
        vurl = 'http://vv.video.qq.com/getkey';
        try:
            response = requests.post('http://vv.video.qq.com/getkey', data=data)
            keys = re.findall('<key>([\s\S]+?)</key>', response.text)
            if len(keys) != 0:
                video_url = 'http://videohy.tc.qq.com/video.dispatch.tc.qq.com/%s.mp4?vkey=%s&ocid=2692093356' % (
                vid, keys[0].strip())
                ext = ".mp4"
                ret = urlparse.urlsplit(video_url)
                items = ret.path.split('/')
                today_str = datetime.date.today().strftime("%Y-%m-%d")
                if items[-1]:
                    idx = items[-1].find(".")
                    ext = items[-1][idx:]
                response = requests.get(video_url)
                self.save_vedio(response.content, guid)
        finally:
            pass

    def save_img(self, response):
        content = response.content
        image_path = self.deal.getImageDirPath()
        file_name = response.save['file_name']
        guid = response.save['guid']
        file_path = image_path + '/' + file_name
        self.deal.saveImg(content, file_path)
        self.upload_image_to_weibo(file_path, guid, file_name)

    def upload_image_to_weibo(self, file_path, guid, file_name):
        data = {'guid': guid, "fileName": file_name}
        files = {'file': open(file_path, 'rb')}
        response = requests.post(UPLOAD_IMAGE_URL, data=data, files=files)
        return {
            "upload_image": response.text
        }

    def save_vedio(self, content, guid):
        import threading
        ext = ".mp4"
        file_name = guid + ext
        video_path = self.deal.getVideoDirPath()
        file_path = video_path + '/' + file_name
        self.deal.saveVedio(content, file_path)
        os.system('ffmpeg -i %s -y -f  image2  -ss 1 -vframes 1  %s' % (file_path, file_path.replace('.mp4', '.jpg')))

    def cut_video(self, shell):
        os.system(shell)


class Deal:
    def __init__(self):
        today_str = datetime.date.today().strftime("%Y-%m-%d")
        self.mkDir('%s/%s' % (IMAGE_DIR_PATH, today_str))
        self.mkDir('%s/%s' % (VIDEO_DIR_PATH, today_str))

    def getImageDirPath(self):
        today_str = datetime.date.today().strftime("%Y-%m-%d")
        return '%s/%s' % (IMAGE_DIR_PATH, today_str);

    def getVideoDirPath(self):
        today_str = datetime.date.today().strftime("%Y-%m-%d")
        return '%s/%s' % (VIDEO_DIR_PATH, today_str);

    def mkDir(self, path):
        path = path.strip()
        exists = os.path.exists(path)
        if not exists:
            os.makedirs(path)
            return path
        else:
            return path

    def saveImg(self, content, path):
        f = open(path, 'wb')
        f.write(content)
        f.close()

    def saveVedio(self, content, path):
        f = open(path, 'wb')
        f.write(content)
        f.close()

    def getExtension(self, url):
        extension = url.split('.')[-1]
        return extension

    #将HTML中标签等信息去掉
    #@param htmlstr HTML字符串.'''
    def filterTag(self, htmlstr):
        re_cdata = re.compile('<!DOCTYPE HTML PUBLIC[^>]*>', re.I)
        re_script = re.compile('<\s*script[^>]*>[^<]*<\s*/\s*script\s*>', re.I) #过滤脚本
        re_style = re.compile('<\s*style[^>]*>[^<]*<\s*/\s*style\s*>', re.I) #过滤style
        re_br = re.compile('<br\s*?/?>')
        re_h = re.compile('</?\w+[^>]*>')
        re_comment = re.compile('<!--[\s\S]*-->')
        s = re_cdata.sub('', htmlstr)
        s = re_script.sub('', s)
        s=re_style.sub('',s)
        s=re_br.sub('\n',s)
        s=re_h.sub(' ',s)
        s=re_comment.sub('',s)
        blank_line=re.compile('\n+')
        s=blank_line.sub('\n',s)
        s=re.sub('\s+',' ',s)
        s=self.replaceCharEntity(s)
        return s

    '''##替换常用HTML字符实体.
    #使用正常的字符替换HTML中特殊的字符实体.
    #你可以添加新的实体字符到CHAR_ENTITIES中,处理更多HTML字符实体.
    #@param htmlstr HTML字符串.'''
    def replaceCharEntity(self, htmlstr):
        CHAR_ENTITIES={'nbsp':'','160':'',
                        'lt':'<','60':'<',
                        'gt':'>','62':'>',
                        'amp':'&','38':'&',
                        'quot':'"''"','34':'"'}
        re_charEntity=re.compile(r'&#?(?P<name>\w+);') #命名组,把 匹配字段中\w+的部分命名为name,可以用group函数获取
        sz=re_charEntity.search(htmlstr)
        while sz:
            #entity=sz.group()
            key=sz.group('name') #命名组的获取
            try:
                htmlstr=re_charEntity.sub(CHAR_ENTITIES[key],htmlstr,1) #1表示替换第一个匹配
                sz=re_charEntity.search(htmlstr)
            except KeyError:
                htmlstr=re_charEntity.sub('',htmlstr,1)
                sz=re_charEntity.search(htmlstr)
        return htmlstr