资讯专栏INFORMATION COLUMN

爬虫爬取微信小程序

qianfeng / 784人阅读

摘要:之前打算做个微信小程序的社区,所以写了爬虫去爬取微信小程序,后面发现做微信小程序没有前途,就把原来的项目废弃了做了现在的网站观点不过代码放着也是放着,还不如公开让大家用,所以我把代码贴出来,有需要的复制了使用就是了。

之前打算做个微信小程序的社区,所以写了爬虫去爬取微信小程序,后面发现做微信小程序没有前途,就把原来的项目废弃了做了现在的网站观点,不过代码放着也是放着,还不如公开让大家用,所以我把代码贴出来,有需要的复制了使用就是了。

#coding:utf-8
__author__ = "haoning"
#!/usr/bin/env python
import time
import urllib2
import datetime
import requests
import json
import random
import sys
import platform
import uuid
reload(sys)
sys.setdefaultencoding( "utf-8" )
import re
import os
import MySQLdb as mdb
from bs4 import BeautifulSoup

DB_HOST = "127.0.0.1"
DB_USER = "root"
DB_PASS = "root"
#init database
conn = mdb.connect(DB_HOST, DB_USER, DB_PASS, "pybbs-springboot", charset="utf8")
conn.autocommit(False)
curr = conn.cursor()

count=0
how_many=0

base_url="http://www.wechat-cloud.com"
url=base_url+"/index.php?s=/home/article/ajax_get_list.html&category_id={category_id}&page={page}&size={size}"

user_agents = [
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11",
    "Opera/9.25 (Windows NT 5.1; U; en)",
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
    "Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Kubuntu)",
    "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.12) Gecko/20070731 Ubuntu/dapper-security Firefox/1.5.0.12",
    "Lynx/2.8.5rel.1 libwww-FM/2.14 SSL-MM/1.4.1 GNUTLS/1.2.9",
    "Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.7 (KHTML, like Gecko) Ubuntu/11.04 Chromium/16.0.912.77 Chrome/16.0.912.77 Safari/535.7",
    "Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:10.0) Gecko/20100101 Firefox/10.0 ",
]

def fake_header():
    agent=random.choice(user_agents)
    cookie="PHPSESSID=p5mokvec7ct1gqe9efcnth9d44; Hm_lvt_c364957e96174b029f292041f7d822b7=1487492811,1487556626; Hm_lpvt_c364957e96174b029f292041f7d822b7=1487564069"
    req_header = {
        "Accept":"application/json, text/javascript, */*; q=0.01",
        #"Accept-Encoding":"gzip, deflate, sdch",
        "Accept-Language":"zh-CN,zh;q=0.8",
        "Cache-Control":"max-age=0",
        "Connection":"keep-alive",
        "Host":"www.wechat-cloud.com",
        #"Cookie":cookie,
        "Referer":"http://www.wechat-cloud.com/index.php?s=/home/index/index.html",
        "Upgrade-Insecure-Requests":"1",
        "User-Agent":agent,
        "X-Requested-With":"XMLHttpRequest",
    }
    return req_header

def gethtml(url):
    try:
        header=fake_header()
        req = urllib2.Request(url,headers=header)
        response = urllib2.urlopen(req, None,15)
        html = response.read()
        return html
    except Exception as e:
        print "e",e
    return None


def get_img_data(url):
    try:
        #添加头信息,模仿浏览器抓取网页,对付返回403禁止访问的问题
        req = urllib2.Request(url)
        response = urllib2.urlopen(req, None,15)
        dataimg = response.read()
        return dataimg
    except Exception as e:
        print "image data",e
    return None

def makeDateFolder(par,classify):
    try:
        if os.path.isdir(par):
            newFolderName=par + "//" + str(classify)+ "//" +GetDateString() 
            if not os.path.isdir( newFolderName ):
                os.makedirs( newFolderName )
            return newFolderName
        else:
            return par 
    except Exception,e:
        print "kk",e
    return par  

def map_folder(what):
    return what

def GetDateString():
    when=time.strftime("%Y-%m-%d",time.localtime(time.time()))
    foldername = str(when)
    return foldername 

def get_extension(name):  
    where=name.rfind(".")
    if where!=-1:
        return name[where:len(name)]
    return "#"

def download_img(url,what):
    try:
        #print url
        extention=get_extension(url)
        dataimg=get_img_data(url)
        name=str(uuid.uuid1()).replace("-","")+"-www.weixinapphome.com"
        #print "name",name
        classfiy_folder=map_folder(what)
        top="E://wxapp_store"
        filename  =makeDateFolder(top,classfiy_folder)+"//"+name+extention
        try:
            if not os.path.exists(filename):
                file_object = open(filename,"w+b")
                file_object.write(dataimg)
                file_object.close()
                return classfiy_folder+"/"+GetDateString()+"/"+name+extention
            else:
                print "file exist"
                return None
        except IOError,e1:
            print "e1=",e1
            #pass
        return None #如果没有下载下来就利用原来网站的链接
    except Exception,e:
        print "problem",e
        pass
    return None
    
    
def work():
    page=0
    global how_many
    while 1:
        try:
            page=page+1
            begin_url=url.format(category_id=0, page=page,size=12).encode("utf-8")
            html=gethtml(begin_url)
            if html is not None:
                #print html
                json_results=json.loads(html)
                is_end=json_results["isEnd"]
                if str(is_end)=="True":
                    break
                results=json_results["list"]
                for result in results:
                    href=result["href"]
                    detail_url=base_url+href
                    #print detail_url
                    detail_html=gethtml(detail_url)
                    if detail_html is not None:
                        soup = BeautifulSoup(detail_html)
                        icon_url=base_url+soup.find("div",{"class":"icon fl"}).find("img").get("src")
                        name=soup.find("div",{"class":"cont fl"}).find("h2").text
                        classify=soup.find("div",{"class":"tab"}).find("span").text
                        classify=str(classify).replace("分类: ","")
                        #print classify
                        barcode_path=base_url+soup.find("div",{"id":"install-code"}).find("img").get("src")
                        view_num=soup.find("span",{"class":"views"}).text
                        #view_num=filter(str.isalnum,str(view_num))
                        pic_path=base_url+soup.find("div",{"class":"img-box"}).find("img").get("src")
                        temp = time.time()
                        x = time.localtime(float(temp))
                        acq_time = time.strftime("%Y-%m-%d %H:%M:%S",x) # get time now
                        curr.execute("select id from pybbs_wxapp_store where `from`=%s",(detail_url))
                        y= curr.fetchone()
                        if not y:
                            y1=download_img(icon_url,"icon")
                            y2=download_img(barcode_path,"barcode")
                            y3=download_img(pic_path,"pic")
                            if (y1 is not None) and (y2 is not None) and (y3 is not None):
                                name=name
                                author=None
                                classify=classify
                                describe=None
                                view_num=view_num
                                #print view_num
                                logo=y1
                                _from=detail_url
                                barcode=y2
                                acq_time=acq_time
                                hot_weight=-9999
                                pic_uuid=str(uuid.uuid1()).replace("-","")
                                pic_path=y3
                                #print name,author,classify,describe,view_num,logo,_from,barcode,acq_time,hot_weight,pic_uuid
                                curr.execute("INSERT INTO pybbs_wxapp_store(name,author,classify,`describe`,view_num,logo,`from`,barcode,acq_time,hot_weight,pic_path)VALUES(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)",(name,author,classify,describe,view_num,logo,_from,barcode,acq_time,hot_weight,pic_path))
                                curr.execute("select id from pybbs_wxapp_classify where `classify_name`=%s",(classify))
                                yx= curr.fetchone()
                                if not yx:
                                    describe=None
                                    temp = time.time()
                                    x = time.localtime(float(temp))
                                    record_time = time.strftime("%Y-%m-%d %H:%M:%S",x) # get time now
                                    curr.execute("INSERT INTO pybbs_wxapp_classify(classify_name,`describe`,record_time)VALUES(%s,%s,%s)",(classify,describe,record_time))
                                how_many+=1
                                print "new comer:",pic_uuid,">>",how_many
                                if how_many % 10==0:
                                    conn.commit()
                conn.commit()
        except Exception as e:
            print "while error",e

if __name__ == "__main__":
    i=3
    while i>0:
        work()
        i=i-1

其中有些参数请改成自己的,比如说数据库密码了,图片存储到哪个盘,数据库表格自己建立,因为这些实在太简单了,所以没啥可以唠叨的。

文章版权归作者所有,未经允许请勿转载,若此文章存在违规行为,您可以联系管理员删除。

转载请注明本文地址:https://www.ucloud.cn/yun/41197.html

相关文章

  • 首次公开,整理12年积累的博客收藏夹,零距离展示《收藏夹吃灰》系列博客

    摘要:时间永远都过得那么快,一晃从年注册,到现在已经过去了年那些被我藏在收藏夹吃灰的文章,已经太多了,是时候把他们整理一下了。那是因为收藏夹太乱,橡皮擦给设置私密了,不收拾不好看呀。 ...

    Harriet666 评论0 收藏0
  • Scrapy学习(四) 取微博数据

    摘要:爬虫目标是获取用户的微博数关注数粉丝数。创建数据这部分我只需要个人信息,微博数,关注数分数数这些基本信息就行。 前言 Scrapy学习(三) 爬取豆瓣图书信息 接上篇之后。这次来爬取需要登录才能访问的微博。爬虫目标是获取用户的微博数、关注数、粉丝数。为建立用户关系图(尚未实现)做数据储备 准备 安装第三方库requests和pymongo 安装MongoDB 创建一个weibo爬虫项...

    LiveVideoStack 评论0 收藏0
  • 利用新浪API实现数据的抓取微博数据取微爬虫

    摘要:本人长期出售超大量微博数据旅游网站评论数据,并提供各种指定数据爬取服务,。如果用户传入伪造的,则新浪微博会返回一个错误。 PS:(本人长期出售超大量微博数据、旅游网站评论数据,并提供各种指定数据爬取服务,Message to YuboonaZhang@Yahoo.com。由于微博接口更新后限制增大,这个代码已经不能用来爬数据了。如果只是为了收集数据可以咨询我的邮箱,如果是为了学习爬虫,...

    liuyix 评论0 收藏0
  • 利用新浪API实现数据的抓取微博数据取微爬虫

    摘要:本人长期出售超大量微博数据旅游网站评论数据,并提供各种指定数据爬取服务,。如果用户传入伪造的,则新浪微博会返回一个错误。 PS:(本人长期出售超大量微博数据、旅游网站评论数据,并提供各种指定数据爬取服务,Message to YuboonaZhang@Yahoo.com。由于微博接口更新后限制增大,这个代码已经不能用来爬数据了。如果只是为了收集数据可以咨询我的邮箱,如果是为了学习爬虫,...

    vslam 评论0 收藏0

发表评论

0条评论

qianfeng

|高级讲师

TA的文章

阅读更多
最新活动
阅读需要支付1元查看
<