36漫画单线程爬虫
本帖最后由 hksnow 于 2019-8-2 22:52 编辑软件截图:
使用单线程下载，不容易卡死，自动设置下载目录，防止下载文件不知道搞到了哪里。
代码比较乱，使用正则对信息进行处理
#-*- coding:utf-8 -*-
import requests
import re
import os
headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:68.0) Gecko/20100101 Firefox/68.0'
}
def download(url,chapters_name,title,path):
html = requests.get(url,headers = headers)
text = re.findall('<body class="clearfix">(.*?)<div class="chapter-view">',html.text,re.S)
chapterImages = re.findall('(\\[[^\\]]*\\])',text,re.S)
host = re.findall('pageImage = "(.*?)";',text,re.S).split('/')
chapterPath = re.findall('chapterPath = "(.*?)"',text,re.S)
#print(host)
#print(chapterImages)
chapterImages_list = eval(chapterImages)
for x in chapterImages_list:
print(x)
download_url = 'http://' + host + '/' + chapterPath +x
print(download_url)
file1 = requests.get(download_url,headers = headers)
with open(path + '\\' + x,'ab') as code:
code.write(file1.content)
def get_chapter(url):
html = requests.get(url,headers = headers)
html.encoding='utf-8'
text = re.findall('<div class="chapter-body clearfix">(.*?)<div class="chapter-category clearfix">',html.text,re.S).replace('\n','').replace(' ','')
#print(data)
title = re.findall('<h1><span>(.*?)</span></h1>',html.text,re.S)
data = re.findall('<li><ahref="(.*?)"class=""><span>(.*?)</span>',text,re.S)
print(title)
for x in data:
url = 'https://www.36mh.com' + x
chapters_name = x
print(chapters_name)
path1 = os.getcwd()
path2 = path1 + '\\' + title + '\\' + chapters_name
os.makedirs(path2)
#print(path2)
download(url,chapters_name,title,path2)
if __name__ == '__main__':
print('请输入链接，例如：https://www.36mh.com/manhua/yukuaideshiyi/')
url = input()
get_chapter(url)
这个漫画
https://www.36mh.com/manhua/yukuaideshiyi/
我去好好看看{:1_918:}
Niuer 发表于 2019-8-2 23:17
大佬求点python教程看，有的话给个链接。
https://www.liaoxuefeng.com/
我入门看的这个 linux py 2.6.5对ua报错
SyntaxError: invalid syntax 大佬求点python教程看，有的话给个链接。
页:
[1]