python Beautiful Soup 采集it books pdf,免费下载

http://www.allitebooks.org/
是我见过最良心的网站,所有书籍免费下载
周末无聊,尝试采集此站所有Pdf书籍。

采用技术

  • python3.5
  • Beautiful soup

    分享代码

    最简单的爬虫,没有考虑太多的容错,建议大家尝试的时候,温柔点,别把这个良心网站搞挂掉了

# www.qingmiaokeji.cn 30
from bs4 import BeautifulSoup
import requests
import json

siteUrl = 'http://www.allitebooks.org/'


def category():
    response = requests.get(siteUrl)
    # print(response.text)
    categoryurl = []
    soup = BeautifulSoup(response.text,"html.parser")
    for a in soup.select('.sub-menu li a'):
        categoryurl.append({'name':a.get_text(),'href':a.get("href")})
    return categoryurl

def  bookUrlList(url):
    # urls = []
    response = requests.get(url['href'])
    soup = BeautifulSoup(response.text,"html.parser")
    a = soup.select(".pagination a[title='Last Page →']")
    nums = 0
    for e in a:
        nums = int(e.get_text())
        # print(e.get_text())
    for i in range(1,nums+1):
        # print(url+"page/"+str(i))
        # urls.append(url+"page/"+str(i))
        bookList(url['href']+"page/"+str(i))

def bookList(url):
    response = requests.get(url)
    soup = BeautifulSoup(response.text,"html.parser")
    article = soup.select(".main-content-inner article .entry-title a")
    for i in article:
        url = i.get("href")
        getBookDetail(url)

def  getBookDetail(url):
    response = requests.get(url)
    soup = BeautifulSoup(response.text,"html.parser")
    title = soup.select(".single-title")[0].text
    imgurl = soup.select(".entry-body-thumbnail .attachment-post-thumbnail")[0].get("src")
    downLoadPdfUrl = soup.select(".download-links a")[0].get("href")
    with open('d:/booklist.txt', 'a+',encoding='utf-8') as f:
        f.write(title+" | ![]("+imgurl+") | "+ downLoadPdfUrl+"\n")


if __name__ == '__main__':
    
    list = category()
    for url in list:
        bookUrlList(url)
上一篇:Python里的17个超赞操作,让你的技法更beautiful


下一篇:Hibernate 的原生 SQL 查询