Python爬虫——从笔趣阁爬小说

这是一个练习作品。用python脚本爬取笔趣阁上面的免费小说。

环境：python3

类库：BeautifulSoup

数据源：http://www.biqukan.cc

原理就是伪装正常http请求，正常访问网页。然后通过bs4重新解析html结构来提取有效数据。

1. config文件

包含了伪装请求头部，数据源配置（如果不考虑扩展其他数据源，可以写死）。

#!/usr/bin/python
#coding:utf-8
import sys
reload(sys)
sys.setdefaultencoding('utf8')

source = {
	'biquge': {
		'base_url': 'http://www.biqukan.cc',
		'category_min': 1,
		'category_max': 2,
		'category_url': 'http://www.biqukan.cc/fenlei{id}/1.html'
	}
}

header = [
	{'User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.76 Mobile Safari/537.36'},
	{'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50'},
	{'User-Agent':'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)'},
	{'User-Agent':'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1'},
	{'User-Agent': 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)'}
]

config.py文件

2. 爬取全部类目小说

#!/usr/bin/python
#coding:utf-8

import random
import requests
import re
from bs4 import BeautifulSoup
#from BeautifulSoup import BeautifulSoup
import sys
reload(sys)
sys.setdefaultencoding('utf8')
from config import source
from config import header
import hashlib
import time

hash_md5 = hashlib.md5()

## 
# 通过分类获取文章名和对应的链接
# 
def fiction():
	url = source['biquge']['category_url']
	cur_category_name = ''
	_list = {}
	for i in range(source['biquge']['category_min'], source['biquge']['category_max']):
		req = requests.get(url.replace('{id}', '%s'%i), headers = header[random.randint(0,4)])
		_temp_result = req.content.decode('gbk')
		bs = BeautifulSoup(_temp_result, "html.parser")

		next_page = bs.find('ul', id='pagelink')
		while next_page!=None:
			next_page = next_page.find('a', 'next')
			if next_page==None:
				break

			# 更新小说
			_page = _cur_page(bs)
			print('page.length = %d'%len(_page))
			_list.update(_page)

			# 获取下一页数据
			req = requests.get(next_page.attrs['href'], headers = header[random.randint(0,4)])
			_temp_result = req.content.decode('gbk')
			bs = BeautifulSoup(_temp_result, "html.parser")
			next_page = bs.find('ul', id='pagelink')

			# 短暂休息一下
			time.sleep(random.random())

	return _list

## 
# 当前页面的所有小说信息
# 
def _cur_page(bs):
	_list = {}
	# top列表
	li_tags = bs.findAll('li', 'list-group-item')
	if li_tags==None or len(li_tags)<=0:
		return _list

	for item in li_tags:
		a_tag = item.find('a')
		_item = {'name':a_tag.get_text(), 'link': a_tag.attrs['href']}

		# 作者
		author = item.find('small').get_text().replace('/ ', '')
		_item['author'] = author

		# 阅读数
		readers = item.find('span').get_text()
		_item['readers'] = readers

		hash_md5.update(_item['link'])
		_list[hash_md5.hexdigest()] = _item

	# 最近更新列表
	tr_tags = bs.findAll('tr')
	if tr_tags==None or len(tr_tags)<=1:
		return _list

	for item in tr_tags:
		a_tag = item.find('a')
		if a_tag==None:
			continue

		_item = {'name':a_tag.get_text(), 'link': a_tag.attrs['href']}

		# 作者
		author = item.find('td', 'text-muted').get_text()
		_item['author'] = author

		# 状态
		status = item.findAll('td')
		_item['status'] = status[len(status)-1].get_text()

		hash_md5.update(_item['link'])
		if _list.has_key(hash_md5.hexdigest())!=True:
			_list[hash_md5.hexdigest()] = _item
		else:
			_list[hash_md5.hexdigest()]['status'] = _item['status']

	return _list


if __name__=="__main__": 
    _temp = fiction()
    print('done')

fiction.py文件

3. 爬取小说介绍信息

#!/usr/bin/python
#coding:utf-8

import random
import requests
import re
from bs4 import BeautifulSoup
#from BeautifulSoup import BeautifulSoup
import sys
reload(sys)
sys.setdefaultencoding('utf8')
from config import source
from config import header

##
# 抓取简介，返回结构体
# 标题：知否？知否？应是绿肥红瘦
# 作者：关心则乱
# 分类：都市言情
# 字数：200万
# 阅读数：2w+
# 状态：连载中、完结
# 封面：url
# 简介：赵丽颖、冯绍峰主演电视剧《知否？知否？应是绿肥红瘦》原著，该剧由正午阳光影业出品，侯鸿亮任制片人，2017年9月6日开机。宅斗翘楚、古言大神关心则乱，手把手传授你实用的古代生存指南。一个消极怠工的古代庶女，生活如此艰难，何必卖力奋斗。古代贵族女子的人生基调是由家族决定的，还流行株连，一个飞来横祸就会彻底遭殃，要活好活顺活出尊严，明兰表示，鸭梨很大。古代太危险了，咱们还是睡死算了。
# 
def summary(url):
	_result={'title':'', 'author':'', 'category':'', 'words':'', 'readers':'', 'status':'', 'cover_img':'', 'summary':''}

	req = requests.get(url,headers = header[random.randint(0,4)])
	_temp_result = req.content.decode('gbk')
	bs = BeautifulSoup(_temp_result, "html.parser")
	
	title_tag = bs.find('h1', 'bookTitle')
	if title_tag!=None:
		_result['title'] = title_tag.get_text()

	book_tag = bs.find('p', 'booktag')
	if book_tag!=None:
		a_tags = book_tag.findAll('a')
		_result['author'] = a_tags[0].get_text()
		_result['category'] = a_tags[1].get_text()

		span_tags = book_tag.findAll('span')
		_result['words'] = span_tags[0].get_text()
		_result['readers'] = span_tags[1].get_text()
		_result['status'] = span_tags[2].get_text()

	intro_tag = bs.find('p', id='bookIntro')
	_result['cover_img'] = intro_tag.find('img').attrs['src']
	_result['summary'] = intro_tag.get_text().replace('\n\r\n                            ','').replace('\r\n                        ','')

	return _result


if __name__=="__main__": 
    _temp = summary('http://www.biqukan.cc/book/47583/')
    print(_temp)

summary.py文件

4. 爬取小说目录

#!/usr/bin/python
#coding:utf-8

import random
import requests
import re
from bs4 import BeautifulSoup
#from BeautifulSoup import BeautifulSoup
import sys
reload(sys)
sys.setdefaultencoding('utf8')
from config import source
from config import header

# 抓取目录
def catalog(url):
	_list=[]
	req = requests.get(url,headers = header[random.randint(0,4)])
	_temp_result = req.content.decode('gbk')
	bs = BeautifulSoup(_temp_result, "html.parser")
	
	all_list = bs.find('div', id='list-chapterAll')
	if all_list==None:
		return _list

	list_tag = all_list.find('dl', 'panel-chapterlist')
	if list_tag==None:
		return _list

	a_tags = list_tag.findAll('a')
	for k in a_tags:
		_dict={}
		_dict['name'] = k.get_text()
		_dict['link'] = url + k.attrs['href']
		_list.append(_dict)
	
	return _list


if __name__=="__main__": 
    _temp = catalog('http://www.biqukan.cc/book/47583/')
    print(_temp)

catalog.py文件

5. 爬取小说正文

#!/usr/bin/python
#coding:utf-8

import random
import requests
import re
from bs4 import BeautifulSoup
#from BeautifulSoup import BeautifulSoup
import sys
reload(sys)
sys.setdefaultencoding('utf8')
from config import source
from config import header

##
# 抓取小说正文
#
def detail(url):
	per_artitle_limit_page = 3;
	title=''
	content=''
	for i in range(1, per_artitle_limit_page):
		if i==1:
			part_url = ''
		else:
			part_url = '_%s'%i

		req = requests.get(url.replace('.html',part_url + '.html'),headers = header[random.randint(0,4)])
		_temp_result = req.content.decode('gbk')
		bs = BeautifulSoup(_temp_result, "html.parser")

		# title
		if len(title)<=0:
			title = bs.find('li','active').get_text()#re.findall(title_re, _temp_result)[0]

		
		content_tag = bs.find('div', id='htmlContent')
		if content_tag==None:
			break
		
		next_tag = content_tag.find('p', 'text-danger')
		if next_tag!=None:
			next_tag.clear()
		_ = content_tag.get_text().replace('-->>', '').replace('一秒记住【笔趣阁 www.biqukan.cc】，更新快，无弹窗，免费读！','')
		content += _
	return content


def filter(content):
	_temp = content.split('\r\n')
	for index in range(len(_temp)):
		_temp[index] = _temp[index].replace(' ','')
	_temp = [elem for elem in _temp if elem != None and len(elem) != 0]
	return ''.join(_temp)


if __name__=="__main__": 
    _temp = detail('http://www.biqukan.cc/book/20461/12592815.html')
    print(filter(_temp))

article.py文件

总结：

暂没有做数据保存模块。如果需要串起来做成一个完整的项目的话，只需要把小说数据结构保存即可（节省磁盘空间）。通过小说url可以很快速的提取出小说简介、目录、每一章的正文。

如果想要做的更好，可以把目录，介绍、正文等部分缓存起来，当然得有足够的空间。