Python爬取网站小说保存txt，pdf文件

最新推荐文章于 2024-01-20 14:31:26 发布

行_歌

最新推荐文章于 2024-01-20 14:31:26 发布

阅读量589

点赞数 2

文章标签： Python 爬虫

本文链接：https://blog.csdn.net/qq_43188211/article/details/103509307

版权

# 爬取小说 http://www.hengyan.com/dir/9495.aspx

from lxml.html import etree
import requests
import re
import os
import pdfkit

host = "http://www.hengyan.com"
url = "http://www.hengyan.com/dir/9495.aspx"
temp = ''
outPutDirName = 'D:/Book/'
config = pdfkit.configuration(wkhtmltopdf=r"D:\Program Files\wkhtmltopdf\bin\wkhtmltopdf.exe")

if not os.path.exists(outPutDirName):
    # 如果文件目录不存在则创建目录
    os.makedirs(outPutDirName)

response = requests.get(url)
selector = etree.HTML(response.text)

for i in range(1, 43):
	words = selector.xpath('//*[@id="left"]/div[3]/ul/li[' + str(i) + ']/a/text()')
	hrefs = selector.xpath('//*[@id="left"]/div[3]/ul/li[' + str(i) + ']/a/@href')
	address = host + ''.join(hrefs)
	print(words, address)

	html = requests.get(address)
	content = etree.HTML(html.text)
	block = content.xpath('//*[@class="contentitem"]/div[3]')
	sub_str = re.sub(u"([^\u4e00-\u9fa5\u0030-\u0039\u0041-\u005a\u0061-\u007a-\u3000])", "", str(''.join(words)))  # 剔除非法字符
	filename = outPutDirName + sub_str + '.txt'

	for j in block:
		aaa = j.xpath('./p/text()')
		bbb = '\n'.join(aaa)
		bbb.strip()
		bbb.replace(' ', '')
		# print(bbb)
		file = open(filename , 'w')
		file.write(bbb)

	file.close()
	temp = temp + '\n'.join(words) + '</br>' + bbb + '</br>'
	temp.replace('\n', '</br>')
# 写成pdf
last_pdf = '<html><head><meta charset="UTF-8"></head>' \
       '<body><div align="center"><p>%s</p></div></body></html>' %temp

pdfkit.from_string(last_pdf, "./民间烧尸怪谈.pdf", configuration=config)

行_歌

关注

2
点赞
踩
0

收藏

觉得还不错? 一键收藏
2
评论
Python爬取网站小说保存txt，pdf文件

# 爬取小说 http://www.hengyan.com/dir/9495.aspxfrom lxml.html import etreeimport requestsimport reimport osimport pdfkithost = "http://www.hengyan.com"url = "http://www.hengyan.com/dir/9495.aspx...
复制链接

扫一扫