· Python 3.6
· Pycharm
输入想看的小说内容，点击搜索
这里会返回很多结果，我只选择第一个
网页数据是静态数据，但是要搜索，是post请求，需要提价data参数，如下图所示：
然后通过解析网站数据，获取第一个小说i的详情页url即可
def search():
search_url = 'http://www.xbiquge.la/modules/article/waps.php'
data = {
'searchkey': name
}
response = requests.post(url=search_url, data=data, headers=headers)
selector = get_parsing(response.text)
novel_url = selector.css('.even a::attr(href)').extract_first()
所有的章节名以及url地址，都包含在dd标签里面
'/23/23019/11409705.html' # 这是网页获取到的url 'http://www.xbiquge.la/23/23019/11409705.html' # 这是真实的小说章节内容url地址
def download_one_book(index_url):
response = get_response(index_url)
response.encoding = response.apparent_encoding
sel = get_parsing(response.text)
book_name = sel.css('#info h1::text').get()
# 提取了所有章节的下载地址
urls = sel.css('#list dd a::attr(href)').getall()
# 不要最新的 12 章放在最前main
for url in urls:
chapter_url = 'http://www.xbiquge.la' + url
print(chapter_url)
保存下载每章小说内容
def download_one_chapter(chapter_url, book_name):
response = get_response(chapter_url)
response.encoding = response.apparent_encoding
html = response.text
selector = get_parsing(html)
h1 = selector.css('.bookname h1::text').get()
content = selector.css('#content::text').getall()
lines = []
for c in content:
lines.append(c.strip())
print(h1)
text = '\n'.join(lines)
file = open(book_name + '.txt', mode='a', encoding='utf-8')
file.write(h1)
file.write('\n')
file.write(text)
file.write('\n')
file.close()
root = Tk()
root.title('小说下载器')
root.geometry('560x450+400+200')
label = Label(root, text='请输入下载小说名字:', font=('华文行楷', 20))
label.grid()
entry = Entry(root, font=('隶书', 20))
entry.grid(row=0, column=1)
text = Listbox(root, font=('隶书', 16), width=50, heigh=15)
text.grid(row=2, columnspan=2)
button1 = Button(root, text='开始下载', font=('隶书', 15), command=search)
button1.grid(row=3, column=0)
button2 = Button(root, text='退出程序', font=('隶书', 15), command=root.quit)
button2.grid(row=3, column=1)
root.mainloop()
def novel_load(title):
text.insert(END, '正在保存：{}'.format(title))
# 文本框滚动
text.see(END)
# 更新
text.update()
