# 公众号：一行数据
from bs4 import BeautifulSoup
import requests
import re
 
 
# 获取每本书的链接
def get_book_urls(url):
    book_urls = []
 
    index = requests.get("http://www.daomubiji.com/")
    soup = BeautifulSoup(index.content.decode("utf8"), 'lxml')
 
    articles = soup.find_all("article", class_='article-content')
    for article in articles:
        links = article.find_all('a', href=re.compile("dao-mu-bi-ji"))
        for link in links:
            book_urls.append(link["href"])
 
    return book_urls
 
 
# 获取每章的链接
def get_chapter_urls(url):
    chapter_urls = []
    page = requests.get(url)
    soup = BeautifulSoup(page.content.decode("utf8"), "lxml")
 
    articles = soup.find_all("article", class_="excerpt excerpt-c3")
    for article in articles:
        chapter_urls.append(article.a["href"])
 
    return chapter_urls
 
 
# 获取每章的内容
def get_content(url):
    content = ""
    page = requests.get(url)
    soup = BeautifulSoup(page.content.decode("utf8"), "lxml")
 
    title = soup.find_all("h1", class_="article-title")[0].string
    content += ("\n" + title + "\n\n")
 
    articles = soup.find_all("article", class_="article-content")
    for article in articles:
        ps = article.find_all('p')
        for p in ps:
            for string in p.strings:
                content = content + string + "\n"
 
    return content
 
 
# 获取全本《盗墓笔记》并保存到文件
def get_article(url):
    print(1)
    book_urls = get_book_urls(url)
    print(1)
    chapter_urls = []
    for url in book_urls:
        print(1)
        # url = "http://www.daomubiji.com/dao-mu-bi-ji-2"
        chapter_urls.extend(get_chapter_urls(url))
    print(chapter_urls)
 
    result = ""
 
    for chapter_url in chapter_urls:
        content = get_content(chapter_url)
        result += content
        print(content)
 
    with open("daomubiji.txt", "a") as f:
        f.write(result.encode("utf8"))
 
 
get_article("http://www.daomubiji.com/")