笔趣阁全站小说爬取
本帖最后由 Raohz520 于 2021-4-24 16:55 编辑笔趣阁全站小说爬取
1.使用了五个模块
import time
import requests#pip install requests
import os
import random
from lxml import etree
import webbrowser2.成品 成品下载地址3.
源代码：
#https://www.biquge.info/wanjiexiaoshuo/ 笔趣阁小说全本爬虫
import time
import requests
import os
import random
from lxml import etree
import webbrowser
header = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.128 Safari/537.36 Edg/89.0.774.77"
}
noName = ['#','/','\\',':','*','?','\"','<','>','|'] #\/:*?"<>|
filePath = './保存小说'
def strZ(_str): #将特殊字符转换为空格
ret = ''
for _ in _str:
if _ in noName:
ret += " "
else:
ret += _
return ret
def main():
webbrowser.open('https://www.biquwx.la/')
if not os.path.exists(filePath):
os.mkdir(filePath)
print('1.爬取指定小说')
print('2.爬取整个站点')
if input('使用哪种方式爬取小说？') == '1':
appintDown()
else :
allDown()
input("按下任意键退出")
def appintDown(): #爬取指定小说前提是网页没错
page_url = input('输入要爬取的小说网站(例如 https://www.biquwx.la/10_10240/) ：')
page = requests.get(url=page_url, headers=header)
if page.status_code == 200:# 响应就爬取
page.encoding = 'utf-8'
page_tree = etree.HTML(page.text)
page_title = page_tree.xpath('//div[@id="info"]/h1/text()')
_filePath = filePath + '/' + page_title
if not os.path.exists(_filePath):
os.mkdir(_filePath)
page_dl_list = page_tree.xpath('//div[@class="box_con"]/div[@id="list"]/dl/dd')
for _ in page_dl_list:
_page_url = page_url + _.xpath('./a/@href')
_page_title = _filePath + '/' + strZ(_.xpath('./a/@title')) + '.txt'
_page = requests.get(_page_url, headers=header)
if _page.status_code == 200:
_page.encoding = 'utf-8'
_tree = etree.HTML(_page.text)
_page_content = _tree.xpath('//div[@id="content"]/text()')
fileContent = ''
for _ in _page_content:
fileContent += _ + '\n'
with open(_page_title, 'w', encoding='utf-8') as fp:
fp.write(fileContent)
print('%s成功下载到本地' % (_page_title))
time.sleep(random.uniform(0.05, 0.2))
def allDown(): #整个站点小说爬取
url = 'https://www.biquge.info/wanjiexiaoshuo/'# 目录
page = requests.get(url=url, headers=header)
if page.status_code == 200:# 响应就爬取
page.encoding = 'utf-8'
tree = etree.HTML(page.text)
page_last = tree.xpath('//div[@class="pagelink"]/a[@class="last"]/text()')
for page_i in range(1, int(page_last)):# 小说页数遍历
url = 'https://www.biquge.info/wanjiexiaoshuo/' + str(page_i)
page = requests.get(url=url, headers=header)
if page.status_code == 200:# 响应就爬取
page.encoding = 'utf-8'
tree = etree.HTML(page.text)
li_list = tree.xpath('//div[@class="novelslistss"]/ul/li')
for li in li_list:
page_url = li.xpath('./span[@class="s2"]/a/@href')# 目录链接
page_title = strZ(li.xpath('./span[@class="s2"]/a/text()'))
page = requests.get(url=page_url, headers=header)
if page.status_code == 200:# 响应就爬取
page.encoding = 'utf-8'
page_tree = etree.HTML(page.text)
_filePath = filePath + '/' + page_title
if not os.path.exists(_filePath):
os.mkdir(_filePath)
page_dl_list = page_tree.xpath('//div[@class="box_con"]/div[@id="list"]/dl/dd')
for _ in page_dl_list:
_page_url = page_url + _.xpath('./a/@href')
_page_title = _filePath + '/' + strZ(_.xpath('./a/@title')) + '.txt'
_page = requests.get(_page_url, headers=header)
if _page.status_code == 200:
_page.encoding = 'utf-8'
_tree = etree.HTML(_page.text)
_page_content = _tree.xpath('//div[@id="content"]/text()')
fileContent = ''
for _ in _page_content:
fileContent += _ + '\n'
with open(_page_title, 'w', encoding='utf-8') as fp:
fp.write(fileContent)
print('%s成功下载到本地' % (_page_title))
time.sleep(random.uniform(0.05, 0.2))
if __name__ == '__main__':
main() dr-pan 发表于 2021-4-24 09:32
最好给我们菜鸟上个软件或成品
这里是编程区，不是精品软件分享区，但是，你把我心里话说出来了，哈哈;www 最好给我们菜鸟上个软件或成品{:1_923:}{:1_889:} 膜拜大神，大神加油啊。 不知道怎么用，请教！ 好东西先试试 我是来学习的，这东东不好爬，收藏了慢慢学，感谢分享 看了一遍 还 是 用 delphi实现 简单 谢谢分享 怎么指定下载哪部小说？
谢谢分享 nice nice