爬取豆瓣top250音乐 时长 出版商 存入Mongo数据库

标签：tor   str   mozilla   win   star   inter   user   debug   dal   

import requests
from lxml import etree
import re
import pymongo
import time

client = pymongo.MongoClient(‘localhost‘,27017)
mydb = client[‘mydb‘]
musictop = mydb[‘musictop‘]

headers ={‘User-Agent‘:‘Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0)‘}

def get_url_music(url):
html = requests.get(url,headers=headers)
selector = etree.HTML(html.text)
music_hrefs = selector.xpath(‘//a[@class="nbg"]/@href‘)
for music_href in music_hrefs:
get_music_info(music_href)

def get_music_info(url):
html = requests.get(url,headers=headers)
selector = etree.HTML(html.text)
name = selector.xpath(‘//*[@id="wrapper"]/h1/span/text()‘)[0]
# author = selector.xpath(‘//*[@id="info"]/span[1]/span/a/text()‘)
author = re.findall(‘表演者:.*?>(.*?)</a>‘,html.text,re.S)
styles = re.findall(‘<span class="pl">流派:</span>&nbsp;(.*?)<br/>‘,html.text,re.S)
if len(styles) == 0:
style = ‘未知‘
else:
style = styles[0].strip()
time = re.findall(‘发行时间:</span>&nbsp;(.*?)<br />‘,html.text,re.S)[0].strip()
publishers = re.findall(‘出版者:.*?>(.*?)</a>‘.html.text,re.S)
if len(publishers) == 0:
publisher = ‘未知‘
else:
publisher = publishers[0].strip()
score = selector.xpath(‘//[@id="interest_sectl"]/div/div[2]/strong/text()‘)[0]
print(name,author,style,time,publisher,score)
info = {
‘name‘:name,
‘author‘:author,
‘style‘:style,
‘time‘:time,
‘publisher‘:publisher,
‘score‘:score
}
musictop.insert_one(info)

if __name__ == ‘__main__‘:
urls = [‘https://music.douban.com/top250?start={}‘,format(str(i)) for i in range(0,250,25)]
for url in urls:
get_url_music(url)
time.sleep(2)
问题：各种数据库安装失败 无法debug各种代码

爬取豆瓣top250音乐 时长 出版商 存入Mongo数据库

标签：tor   str   mozilla   win   star   inter   user   debug   dal   

原文地址：https://www.cnblogs.com/zhentaoFrezt/p/9297854.html