嘿,亲!知识可是无价之宝呢,但咱这精心整理的资料也耗费了不少心血呀。小小地破费一下,绝对物超所值哦!如有下载和支付问题,请联系我们QQ(微信同号):813200300
本次赞助数额为: 2 元微信扫码支付:2 元
请留下您的邮箱,我们将在2小时内将文件发到您的邮箱
运用了requests os re lxml threading queue prettytable bs4
等库,实现了小说的智能选择与爬取。
def find_details(information):
headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/73.0.3683.86 Safari/537.36 '
}
root = "http://www.biquger.com/modules/article/search.php?searchkey=" input_name
response = requests.get(root, headers=headers)
page_content = etree.HTML(response.content)
response.encoding = 'utf-8'
find_first = page_content.xpath('string(//*[@id="wrapper"]/table)')
print(find_first)
print(len(find_first))
find_first_show = page_content.xpath("normalize-space(string(//div[@class='novelslist2']/ul/li[position()>1]))")
global information_first
if len(find_first) <= 1:
str(find_first_show)
print(find_first_show)
input_name_find = input("你所查找的小说仅此一个按1开始下载,按2返回查找页面\n")
if input_name_find.replace(".", '').isdigit():
if input_name_find.count(".") == 0:
if int(input_name_find) == 1:
find_first_a = page_content.xpath(
"//div[@class='novelslist2']/ul/li[position()>1]/span[@class='s2']/a/text()")
print(find_first_a)
index_first = find_first_a.index(input_name)
find_first_href = page_content.xpath(
"//div[@class='novelslist2']/ul/li[position()>1]/span[@class='s2']/a/@href")
information_first = find_first_href[index_first]
return 0
if int(input_name_find) == 2:
request()
find_details(information)
else:
print("请不要输入带点的小数,只能输入1或2 3秒后返回")
time.sleep(3)
find_details(information)
else:
print("请输入1或2 不得输入其他字符 3秒后将返回当前的小说页面")
print("3")
time.sleep(1)
print("2")
time.sleep(1)
print("1")
time.sleep(1)
find_details(information)