• 大小: 5KB
    文件类型: .py
    金币: 1
    下载: 0 次
    发布日期: 2021-06-02
  • 语言: Python
  • 标签: 豆瓣  爬虫  

资源简介

找出评分最高的前100部电影,使用python 实现,对网站爬虫

资源截图

代码片段和文件信息

#-*- coding: UTF-8 -*-

import sys
import time
import urllib
import urllib2
//  import requests
import numpy as np
from bs4 import BeautifulSoup
from openpyxl import Workbook

reload(sys)
sys.setdefaultencoding(‘utf8‘)



#Some User Agents
hds=[{‘User-Agent‘:‘Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6‘}\
{‘User-Agent‘:‘Mozilla/5.0 (Windows NT 6.2) AppleWebKit/535.11 (KHTML like Gecko) Chrome/17.0.963.12 Safari/535.11‘}\
{‘User-Agent‘: ‘Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Trident/6.0)‘}]


def book_spider(book_tag):
    page_num=0;
    book_list=[]
    try_times=0
    
    while(1):
        #url=‘http://www.douban.com/tag/%E5%B0%8F%E8%AF%B4/book?start=0‘ # For Test
        url=‘http://www.douban.com/tag/‘+urllib.quote(book_tag)+‘/book?start=‘+str(page_num*15)
        time.sleep(np.random.rand()*5)
        
        #Last Version
        try:
            req = urllib2.Request(url headers=hds[page_num%len(hds)])
            source_code = urllib2.urlopen(req).read()
            plain_text=str(source_code)   
        except (urllib2.HTTPError urllib2.URLError) e:
            print e
            continue
  
        ##Previous Version IP is easy to be Forbidden
        #source_code = requests.get(url) 
        #plain_text = source_code.text  
        
        soup = BeautifulSoup(plain_text)
        list_soup = soup.find(‘div‘ {‘class‘: ‘mod book-list‘})
        
        try_times+=1;
        if list_soup==None and try_times<200:
            continue
        elif list_soup==None or len(list_soup)<=1:
            break # Break when no informatoin got after 200 times requesting
        
        for book_info in list_soup.findAll(‘dd‘):
            title = book_info.find(‘a‘ {‘class‘:‘title‘}).string.strip()
            desc = book_info.find(‘div‘ {‘class‘:‘desc‘}).string.strip()
            desc_list = desc.split(‘/‘)
            book_url = book_info.find(‘a‘ {‘class‘:‘title‘}).get(‘href‘)
            
            try:
                author_info = ‘作者/译者: ‘ + ‘/‘.join(desc_list[0:-3])
            except:
                author_info =‘作者/译者: 暂无‘
            try:
                pub_info = ‘出版信息: ‘ + ‘/‘.join(desc_list[-3:])
            except:
                pub_info = ‘出版信息: 暂无‘
            try:
                rating = book_info.find(‘span‘ {‘class‘:‘rating_nums‘}).string.strip()
            except:
                rating=‘0.0‘
            try:
                #people_num = book_info.findAll(‘s

评论

共有 条评论