|
| 1 | +import json |
| 2 | +import random |
| 3 | +import time |
| 4 | +import pymongo |
| 5 | +import requests |
| 6 | +from bs4 import BeautifulSoup |
| 7 | +from lxml import etree |
| 8 | + |
| 9 | +clients = pymongo.MongoClient('localhost') |
| 10 | +db = clients["XiMaLaYa"] |
| 11 | +col1 = db["album2"] |
| 12 | +col2 = db["detaile2"] |
| 13 | + |
| 14 | +UA_LIST = [ |
| 15 | + "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1", |
| 16 | + "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11", |
| 17 | + "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6", |
| 18 | + "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6", |
| 19 | + "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1", |
| 20 | + "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5", |
| 21 | + "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5", |
| 22 | + "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", |
| 23 | + "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", |
| 24 | + "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)", |
| 25 | + "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", |
| 26 | + "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", |
| 27 | + "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", |
| 28 | + "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", |
| 29 | + "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3", |
| 30 | + "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24", |
| 31 | + "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24", |
| 32 | + "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1", |
| 33 | + "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11", |
| 34 | + "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6", |
| 35 | + "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6", |
| 36 | + "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1", |
| 37 | + "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5", |
| 38 | + "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5", |
| 39 | + "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", |
| 40 | + "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", |
| 41 | + "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", |
| 42 | + "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", |
| 43 | + "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", |
| 44 | + "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", |
| 45 | + "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", |
| 46 | + "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", |
| 47 | + "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3", |
| 48 | + "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24", |
| 49 | + "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24" |
| 50 | +] |
| 51 | +headers1 = { |
| 52 | + 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8', |
| 53 | + 'Accept-Encoding': 'gzip, deflate, sdch', |
| 54 | + 'Accept-Language': 'zh-CN,zh;q=0.8,en;q=0.6', |
| 55 | + 'Cache-Control': 'max-age=0', |
| 56 | + 'Proxy-Connection': 'keep-alive', |
| 57 | + 'Upgrade-Insecure-Requests': '1', |
| 58 | + 'User-Agent': random.choice(UA_LIST) |
| 59 | +} |
| 60 | +headers2 = { |
| 61 | + 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8', |
| 62 | + 'Accept-Encoding': 'gzip, deflate, sdch', |
| 63 | + 'Accept-Language': 'zh-CN,zh;q=0.8,en;q=0.6', |
| 64 | + 'Cache-Control': 'max-age=0', |
| 65 | + 'Proxy-Connection': 'keep-alive', |
| 66 | + 'Referer': 'http://www.ximalaya.com/dq/all/2', |
| 67 | + 'Upgrade-Insecure-Requests': '1', |
| 68 | + 'User-Agent': random.choice(UA_LIST) |
| 69 | +} |
| 70 | + |
| 71 | + |
| 72 | +def get_url(): |
| 73 | + start_urls = ['http://www.ximalaya.com/dq/all/{}'.format(num) for num in range(1, 85)] |
| 74 | + for start_url in start_urls: |
| 75 | + html = requests.get(start_url, headers=headers1).text |
| 76 | + soup = BeautifulSoup(html, 'lxml') |
| 77 | + for item in soup.find_all(class_="albumfaceOutter"): |
| 78 | + content = { |
| 79 | + 'href': item.a['href'], |
| 80 | + 'title': item.img['alt'], |
| 81 | + 'img_url': item.img['src'] |
| 82 | + } |
| 83 | + col1.insert(content) |
| 84 | + print('写入一个频道' + item.a['href']) |
| 85 | + print(content) |
| 86 | + another(item.a['href']) |
| 87 | + time.sleep(1) |
| 88 | + |
| 89 | + |
| 90 | +def another(url): |
| 91 | + html = requests.get(url, headers=headers2).text |
| 92 | + ifanother = etree.HTML(html).xpath('//div[@class="pagingBar_wrapper"]/a[last()-1]/@data-page') |
| 93 | + if len(ifanother): |
| 94 | + num = ifanother[0] |
| 95 | + print('本频道资源存在' + num + '个页面') |
| 96 | + for n in range(1, int(num)): |
| 97 | + print('开始解析{}个中的第{}个页面'.format(num, n)) |
| 98 | + url2 = url + '?page={}'.format(n) |
| 99 | + get_m4a(url2) |
| 100 | + get_m4a(url) |
| 101 | + |
| 102 | + |
| 103 | +def get_m4a(url): |
| 104 | + time.sleep(1) |
| 105 | + html = requests.get(url, headers=headers2).text |
| 106 | + numlist = etree.HTML(html).xpath('//div[@class="personal_body"]/@sound_ids')[0].split(',') |
| 107 | + for i in numlist: |
| 108 | + murl = 'http://www.ximalaya.com/tracks/{}.json'.format(i) |
| 109 | + html = requests.get(murl, headers=headers1).text |
| 110 | + dic = json.loads(html) |
| 111 | + col2.insert(dic) |
| 112 | + print(murl + '中的数据已被成功插入mongodb') |
| 113 | + |
| 114 | + |
| 115 | +if __name__ == '__main__': |
| 116 | + get_url() |
0 commit comments