晋江年下文爬取xpath

Posted 2022-09-24 chrysanthemum

 

‘‘‘
@Modify Time      @Author   目标：晋江年下文 爬取6页
------------      ------- http://www.jjwxc.net/search.php?kw=%C4%EA%CF%C2&t=1&p=1
2019/8/31 15:19   laoalo
‘‘‘

import requests
from lxml import etree

head = 
    ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/64.0.3282.140 Safari/537.36 Edge/17.17134‘,
    ‘Host‘:‘www.jjwxc.net‘,


def get_page_detail(url):
    # 得到当前页面中每本书的url
    response = requests.get(url=url,headers=head,timeout=50).text
    book = etree.HTML(response).xpath(‘//h3[@class="title"]/a/@href‘)
    # print(etree.tostring(book,encoding=‘gbk‘).decode(‘gbk‘))
    return book

def get_book_detial(book_url):
    # 得到每本书的详细信息
    try:
        response = requests.get(url=book_url, headers=head, timeout=50).text
        book_detail = etree.HTML(response)
        book = 

        title = book_detail.xpath("//span[@itemprop=‘articleSection‘]//text()")[0].encode(‘ISO-8859-1‘).decode(‘gbk‘)
        book[‘title‘] = title
        author = book_detail.xpath("//span[@itemprop=‘author‘]//text()")[0].encode(‘ISO-8859-1‘).decode(‘gbk‘)
        book[‘author‘] = author
        information = book_detail.xpath("string(//div[@id=‘novelintro‘])").encode(‘ISO-8859-1‘).decode(‘gbk‘)
        book[‘information‘] = information

        return book
    except IndexError as e:
        print(e,‘下标越界‘)

    # targets = book_detail.xpath("//text()")
    # for index,target in enumerate(targets):
    #     print(index,‘*‘*30,target.encode(‘ISO-8859-1‘).decode(‘gbk‘))
    # ‘‘‘
    # 标签爬不出来
    # ‘‘‘


def spider():
    bookshelf = []
    for i in range(1,5):
        print("这是第index页的信息\n\n\n".format(index=i))
        url = ‘http://www.jjwxc.net/search.php?kw=%C4%EA%CF%C2&t=1&p=page_num‘.format(page_num=i)
        book_list = get_page_detail(url)
        for i in book_list:
            # print(get_book_detial(i))
            bookshelf.append(get_book_detial(i))
    return bookshelf
        # print(url)
if __name__ == ‘__main__‘:
    # print(get_book_detial("http://www.jjwxc.net/onebook.php?novelid=3402626"))
    print(spider())

时常会有："list index out of range 下标越界"，或是"TimeoutError: [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应，连接尝试失败"，有的师傅说是因为访问过快，导致list的赋值没附上……代码有待优化