Python 爬取 书籍

...

import requests
from bs4 import BeautifulSoup


def gethtml(url,h):
    r = requests.get(url,headers=h)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    return r.text

def getburl(r):
    soup = BeautifulSoup(r,'lxml')
    burls = []
    for url in soup.find_all(class_='top-tit'):
        base_u = url.p.a.attrs['href']
        b_url = 'http://www.jb51.net' + base_u
        burls.append(b_url)
    return burls
def getbhtml(url):
    he = {
        'Host': 'www.jb51.net',
        'Referer': url,
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36'
    }
    r = requests.get(url, headers=he)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    return r.text

def bookinfo(r):
    soup = BeautifulSoup(r, 'lxml')
    name = soup.find(class_='new2').h1.text
    downurl = []
    durls = soup.find(class_='content greena clearfix')
    for a in durls.find_all('a'):
        downurl.append(a.attrs['href'])
    return name,downurl

if __name__ == "__main__":

    h = {
        'Host': 'www.jb51.net',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36'
    }
    # file = open('booksdown.txt', 'a')
    for page in range(1,4):
        url = 'http://www.jb51.net/books/list476_{}.html'.format(str(page))
        r = gethtml(url,h)
        burls = getburl(r)
        for burl in burls:
            br = getbhtml(burl)
            binfos = bookinfo(br)
            print(binfos)
            print('书籍原地址：{}'.format(burl))
            print('\n\n')
    #         file.write(str(binfos))
    #         file.write('\n\n')
    # file.close()

 

转载于:https://www.cnblogs.com/mysterious-killer/p/10157119.html