def getBook(type,page):
"爬取书网址,type=int小说类型,page=int书架页码,book_L=list所有书的地址列表"
hd = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36 SLBrowser/7.0.0.4071 SLBChan/21"}
url = "https://www.duquanben.com/book%d/0/%d/"
url = url % (type,page)
page = requests.get(url,headers=hd)
page.encoding = page.apparent_encoding
soup = BeautifulSoup(page.text, 'html.parser')
dIv = soup.find('div', attrs={'class':"clearfix rec_rullist"})
li = dIv.find_all('li', attrs={'class':"two"})
book_L = []
for i in li:
src = i.a['href']
name = i.a.text
book_L.append((name,src))
return book_L