python爬虫之一(2)：爬取网页小说（圣墟）

强化：
爬取最新的小说圣墟

代码：

#coding=utf-8
import os
import sys
reload(sys)
sys.setdefaultencoding('utf8')
from Spider import getHtmlCode 
from bs4 import BeautifulSoup
import re

#第一章的地址
url = 'https://www.biquge5200.com/52_52542/20380548.html'
def getTree(url):
    temp = getHtmlCode(url)
    soup = BeautifulSoup(temp,'html.parser')
    return soup


#输入为：章节网页地址
#输出为：（章节名，内容）
def getAll(url):
    temp = getTree(url)
    chaptername = temp.h1.string
    print u'章节名：',chaptername
    content = temp.find_all('div',id='content')
    content = str(content[0])
    content = content.replace('
','\n')
    pattern = re.compile('<(.*)>')
    list_line = pattern.findall(content)
    for line in list_line:
        line = '<' + line +'>'
        content = content.replace(line,'')
    # print u'内容 ：',content,'\n'
    return(chaptername,content)

#输入为：章节地址
#输出为：创建一个章节名为文件名的txt文本    
def creatFile(url):
    (fileName,txt) = getAll(url)
    fileName = fileName + '.txt'
    f = open(fileName,'a+')
    f.write(txt)
    f.close()
def nextUrl(url):
    tree = getTree(url)
    aSpan = tree('a',href=re.compile('.*52_52542'))
    for nextChapter in aSpan:
        # print type(nextChapter.string)
        if u'下一章' == nextChapter.string:
            pathUrl = nextChapter['href']
            print pathUrl
            break
        else:
            pathUrl = ''
    return pathUrl
# nextUrl(url)
#输入为：章节地址
#输出为：整本小说（每一百章为一个文件夹放置）
def main(url):
    count = 1
    flag = True
    cmd = 'del /q /s *.txt'
    os.system(cmd)
    while flag:
        creatFile(url)
        print 'adress = ',url
        url = nextUrl(url)
        count = count + 1
        if 0 == (count % 100) :
            filename = count / 100
            cmd_md = 'md ' + str(filename)
            cmd_mv = 'move *.txt ' + str(filename)
            os.system(cmd_md)
            os.system(cmd_mv)
        if -1 == url.find('.html'):
            filename = count / 100 + 1
            cmd_md = 'md ' + str(filename)
            cmd_mv = 'move *.txt ' + str(filename)
            os.system(cmd_md)
            os.system(cmd_mv)
            flag = False
main(url)

结果截图：

在执行时发现这种方式容易报错，后面改为所有章节合并为一本书。
代码：

#coding=utf-8
import os
import sys
reload(sys)
sys.setdefaultencoding('utf8')
from Spider import getHtmlCode 
from bs4 import BeautifulSoup
import re

#第一章的地址
url = 'https://www.biquge5200.com/52_52542/20380548.html'
def getTree(url):
    temp = getHtmlCode(url)
    soup = BeautifulSoup(temp,'html.parser')
    return soup


#输入为：章节网页地址
#输出为：（章节名，内容）
def getAll(url):
    temp = getTree(url)
    chaptername = temp.h1.string
    print u'章节名：',chaptername
    content = temp.find_all('div',id='content')
    content = str(content[0])
    content = content.replace('
','\n')
    pattern = re.compile('<(.*)>')
    list_line = pattern.findall(content)
    for line in list_line:
        line = '<' + line +'>'
        content = content.replace(line,'')
    # print u'内容 ：',content,'\n'
    return(chaptername,content)

#输入为：章节地址
#输出为：创建一个章节名为文件名的txt文本    
def creatFile(url):
    (fileName,txt) = getAll(url)
    txt = fileName + '\n' + txt
    storyFileName = u'圣墟.txt'
    f = open(storyFileName,'a+')
    f.write(txt)
    f.close()
def nextUrl(url):
    tree = getTree(url)
    aSpan = tree('a',href=re.compile('.*52_52542'))
    for nextChapter in aSpan:
        # print type(nextChapter.string)
        if u'下一章' == nextChapter.string:
            pathUrl = nextChapter['href']
            print pathUrl
            break
        else:
            pathUrl = ''
    return pathUrl
# nextUrl(url)
#输入为：章节地址
#输出为：整本小说
def main(url):
    flag = True
    cmd = 'del /q /s *.txt'
    os.system(cmd)
    while flag:
        creatFile(url)
        print 'adress = ',url
        url = nextUrl(url)
        if -1 == url.find('.html'):
            flag = False
main(url)

结果：

（划重点）所有代码以及小说见我的下载资源，没有积分的qq私聊我