使用python-aiohttp爬取今日头条

{
    "has_more": false,
    "message": "success",
    "data": [
        {
            "chinese_tag": "体育",
            "media_avatar_url": "http://p3.pstatp.com/large/3538/9145332",
            "is_feed_ad": false,
            "tag_url": "news_sports",
            "title": "中国足协想搬出北京五环，原来是相中了这块风水宝地",
            "single_mode": true,
            "middle_mode": true,
            "abstract": "中国足协搬家的传说，很可能将水落石出。而且，此前的传说其实很靠谱，中国足协确实有意要从目前位于北京东城区夕照寺街的东玖大厦，搬到京城五环路以外。南海子虽然在北京五环外，但是紧邻南五环，距离位于体育馆路的国家体育总局也不过19公里。",
            "tag": "news_sports",
            "behot_time": 1492391171,
            "source_url": "/group/6409606379224957186/",
            "source": "长安街知事",
            "more_mode": false,
            "article_genre": "article",
            "image_url": "http://p3.pstatp.com/list/190x124/1bf4000b11da52a33c32",
            "has_gallery": false,
            "group_source": 2,
            "comments_count": 28,
            "group_id": "6409606379224957186",
            "media_url": "/c/user/4327876576/"
        },{},{},{},{},{},{}
    ],
    "next": {
        "max_behot_time": 1492391156
    }
}

e.getHoney = function() {
    var t = Math.floor((new Date).getTime() / 1e3),
    e = t.toString(16).toUpperCase(),
    i = md5(t).toString().toUpperCase();
    if (8 != e.length) return {
        as: "479BB4B7254C150",
        cp: "7E0AC8874BB0985"
    };
    for (var n = i.slice(0, 5), a = i.slice( - 5), s = "", o = 0; 5 > o; o++) s += n[o] + e[o];
    for (var r = "",
    c = 0; 5 > c; c++) r += e[c + 3] + a[c];
    return {
        as: "A1" + s + e.slice( - 3),
        cp: e.slice(0, 3) + r + "E1"
    }
}

  1 import asyncio
  2 from aiohttp import ClientSession
  3 import time
  4 import math
  5 import hashlib
  6 
  7 __NEWS_NUM = 1  # hu 返回的最大新闻数
  8 
  9 def getASCP():
 10     t = int(math.floor(time.time()))
 11     e = hex(t).upper()[2:]
 12     m = hashlib.md5()
 13     m.update(str(t).encode(encoding='utf-8'))
 14     i = m.hexdigest().upper()
 15 
 16     if len(e) != 8:
 17         AS = '479BB4B7254C150'
 18         CP = '7E0AC8874BB0985'
 19         return AS,CP
 20 
 21     n = i[0:5]
 22     a = i[-5:]
 23     s = ''
 24     r = ''
 25     for o in range(5):
 26         s += n[o] + e[o]
 27         r += e[o + 3] + a[o]
 28 
 29     AS = 'A1' + s + e[-3:]
 30     CP = e[0:3] + r + 'E1'
 31     return AS,CP
 32 
 33 async def __fetch(url,data,loop):
 34     try:
 35         async with ClientSession(loop=loop) as session:
 36             # hu 发送GET请求，params为GET请求参数，字典类型
 37             async with session.get(url, params=data,timeout=5) as response:
 38                 # hu 以json格式读取响应的body并返回字典类型
 39                 return await response.json()
 40     except Exception as ex:
 41         print('__fetch:%s' % ex)
 42 
 43 async def getNewsInfo(loop):
 44     global __NEWS_NUM
 45     AS,CP = getASCP()
 46     urlTouTiao = 'http://www.toutiao.com'
 47     urlNews = 'http://www.toutiao.com/api/pc/feed/'
 48     dataNew = {'category': 'news_hot',
 49                'utm_source': 'toutiao',
 50                'widen': '1',
 51                'max_behot_time': '0',
 52                'max_behot_time_tmp':'0',
 53                'tadrequire':'true',
 54                'as':AS,
 55                'cp':CP}
 56     result = None
 57     try:
 58         task = asyncio.ensure_future(__fetch(urlNews, dataNew,loop),loop=loop)
 59         taskDone = await asyncio.wait_for(task,timeout=5)
 60         if 'message' not in taskDone or taskDone['message'] != 'success':
 61             return result
 62 
 63         result = {'max_behot_time':taskDone['next']['max_behot_time'],
 64                   'news':[]}
 65 
 66         for news_hot in taskDone['data']:
 67             news = {'Title': None,
 68                     'Description': None,
 69                     'PicUrl': None,
 70                     'Url': None}
 71             # hu 去掉广告
 72             if news_hot['is_feed_ad']:
 73                 continue
 74             news['Title'] = news_hot['title']
 75             if 'abstract' in news_hot:
 76                 news['Description'] = news_hot['abstract']
 77             else:
 78                 news['Description'] = ''
 79             if 'image_url' in news_hot:
 80                 news['PicUrl'] = news_hot['image_url']
 81             else:
 82                 news['PicUrl'] = ''
 83             news['Url'] = urlTouTiao + news_hot['source_url']
 84             result['news'].append(news)
 85             if len(result['news']) == __NEWS_NUM:
 86                 break
 87         # hu 把有图片的新闻放到前面
 88         result['news'].sort(key=lambda obj: obj.get('PicUrl'), reverse=True)
 89     except Exception as ex:
 90         print('getNewsInfo:%s' % ex)
 91     return result
 92 
 93 def __main():
 94     loop = asyncio.get_event_loop()
 95     for ii in range(2):
 96         task = asyncio.ensure_future(getNewsInfo(loop),loop=loop)
 97         taskDone = loop.run_until_complete(task)
 98         print('第%d次：' % ii)
 99         for res in taskDone['news']:
100             print(res)
101     loop.close()
102 
103 if __name__ == '__main__':
104     __main()

 1 #### hu 增加代码 ######
 2 __cookie = None
 3 ######################
 4 
 5 async def __fetch(url,data,loop):
 6     global __cookie
 7     try:
 8         async with ClientSession(cookies=__cookie,loop=loop) as session:
 9             async with session.get(url, params=data,timeout=5) as response:
10 ########################### hu 增加代码 ##############################
11                 if response.cookies and 'tt_webid' in response.cookies:
12                     __cookie = {'tt_webid':response.cookies['tt_webid'].value}
13 #####################################################################
14                 return await response.json()
15     except Exception as ex:
16         print('__fetch:%s' % ex)