Biegral Blog

前言

本文的文字及图片来源于网络,仅供学习、交流使用,不具有任何商业用途,如有问题请及时联系我们以作处理。

PS：如有需要Python学习资料的小伙伴可以加点击下方链接自行获取
python免费学习资料以及群交流解答点击即可加入

抓取漫画的由来也是看了知乎上有人说用爬取漫画，然后自己也玩玩

首页中每个漫画的url是类似这样存储的：

<pre style="margin-top: 0px; margin-bottom: 0px; white-space: pre-wrap; overflow-wrap: break-word; font-family: &quot;Courier New&quot; !important; font-size: 12px !important;"><tr>
     <td height="30" align="center" bgcolor="#FFFFFF">
       <a href="http://comic.sfacg.com/HTML/KOL/" target="_blank">K.O.I 偶像之王</a>
     </td>
</tr></pre>

然后用lxml通过cssselect(tr>td>a)将能用到的解析出来，然后解析出来会有很多其他的页面的url和信息，然后我是通过url中包含"/mh/“或者是”/HTML/"进行过滤的

比较蠢的办法了

然后通过对象，将过滤出来的漫画的url和漫画的名字保存在一个这样的类中，然后通过列表进行存储

class Cartoon():
    url = None
    name = None

然后用随便一个漫画作为例子：勇者赫鲁库

漫画一共很多章，并且所有章的信息都在如下标签中包含

<pre style="margin-top: 0px; margin-bottom: 0px; white-space: pre-wrap; overflow-wrap: break-word; font-family: &quot;Courier New&quot; !important; font-size: 12px !important;"><ul class="serialise_list Blue_link2">....</ul></pre>

然后通过BS将每一章的信息进行存储，然后可以看到其完整的url是：http://comic.sfacg.com/HTML/YZHLK/096/

然后每一章会有很多的page，并且每一章的内容是ajax进行加载的，然后从检查－>网络中可以看到有一个这样的请求

然后请求的response里面包含本章的所有图片，然后只需将在每一章的页面中将.js接口找到，然后将本章的图片信息存储，然后就可以得到本章的图片信息，然后存储到本地

# -*- coding: utf-8 -*-
import re
import urllib
import urllib2
import os
import stat
import itertools
import re
import sys
import requests
import json
import time
import socket
import urlparse
import csv
import random
from datetime import datetime, timedelta
import lxml.html

'''
遇到不懂的问题？Python学习交流群：1136201545满足你的需求，资料都已经上传群文件，可以自行下载！
'''

from zipfile import ZipFile
from StringIO import StringIO
from downloader import Downloader
from bs4 import BeautifulSoup
from HTMLParser import HTMLParser
from itertools import product
import sys
reload(sys)
sys.setdefaultencoding('utf8')
URL = 'http://comic.sfacg.com'
picture = 'http://coldpic.sfacg.com'


class Cartoon():
    url = None
    name = None

def download(url, user_agent='wswp', num_try=2):

    headers = {'User_agent': user_agent}
    request = urllib2.Request(url, headers=headers)
    try:
        html = urllib2.urlopen(request).read()
    except urllib2.URLError as e:
        print 'Download error', e.reason
        html = None
        if num_try > 0:
            if hasattr(e, 'code') and 500 <= e.code < 600:
                return download(url, user_agent, num_try - 1)
            elif e.code == 403:
                return None
    return html

def get_section_url(url):
    html = download(url)
    if html == None:
        return None
    soup = BeautifulSoup(html, "html.parser")
    results = soup.find_all(name='ul', attrs={'class': 'serialise_list Blue_link2'})
    res = r'<a.*?href="([^"]*)".*?>([\S\s]*?)</a>'
    links = re.findall(res, str(results),re.S | re.M)
    return links


def get_section_page(url):

    html = download(url)
    if html == None:
        return None
    soup = BeautifulSoup(html, "html.parser")
    results = soup.find_all(name='script', attrs={'type': 'text/javascript'})
    tt = len(results)
    js = results[tt-1]
    mm = js.get('src')
    if mm == None:
        result = soup.find_all(name='script', attrs={'language': 'javascript'})
        js1 = result[1]
        mm = js1.get('src')
    html1 = download(URL+mm)
    list = html1.split(';')
    List = []
    for each in list:
        if 'picAy[' in each:
            src = each.split('=')
            List.append(picture+src[1][2:-1])

    return List


def download_cartoon(url, cartoon_name,Section,num):

    path = "自己定义的路径"+cartoon_name

    if not os.path.exists(path):
        os.mkdir(path)
    path = path + "/"+Section
    if not os.path.exists(path):
        os.mkdir(path)
    content = requests.get(url).content
    with open(path + '/' + str(num) + '.jpg', 'wb') as f:
        f.write(content)
    print "Downloading cartoon_name " + path + str(num)+ "下载完成"
    f.close()

if __name__ == '__main__':
    cartoon_list = []

    html = download(URL)
    tree = lxml.html.fromstring(html)
    results = tree.cssselect('tr > td > a')
    for each in results:
        ti = each.get('href')
        if '/mh/' in ti or '/HTML/' in ti:
            if each.text_content() != "":
                cartoon = Cartoon()
                cartoon.url = each.get('href')
                cartoon.name = each.text_content().replace(' ','')
                cartoon_list.append(cartoon)

    for each in cartoon_list:
        print each.url
        print each.name
        links = get_section_url(each.url)
        links = list(reversed(links))
        section = 0
        for link in links:
            ul = URL + link[0]
            List = []
            List = get_section_page(ul)
            section = section + 1
            Section = r'第'+ str(section) + r'章'
            num = 1
            for mm in List:
                #print mm
                download_cartoon(mm,each.name,Section,num)
                num = num + 1
            print each.name + Section + "下载完成"+str(num-1)+"张"