107 lines
4.3 KiB
Python
107 lines
4.3 KiB
Python
import os.path
|
|
|
|
import requests
|
|
from lxml import etree
|
|
from fake_useragent import UserAgent
|
|
|
|
class SpiderBiQuGe(object):
|
|
def __init__(self):
|
|
self.headers = {
|
|
"User-Agent":UserAgent().random
|
|
}
|
|
self.novel_name = ""
|
|
self.area = "https://www.bqgie.cc"
|
|
# 根目录
|
|
self.BASE_DIR = os.path.dirname(__file__)
|
|
# 源码文件目录,存储爬取到的每一页的源码数据
|
|
self.SOURCE_DIR = os.path.join(self.BASE_DIR,"novel","source")
|
|
# 文档目录，存储解析到小说的内容
|
|
self.NOVEL_DIR = os.path.join(self.BASE_DIR,"novel","novel")
|
|
def create_tree(self,target_url):
|
|
# 发起请求
|
|
response = requests.get(url=target_url,headers=self.headers)
|
|
# 获取响应
|
|
page_text = response.text
|
|
return page_text ,etree.HTML(page_text)
|
|
# 负责写入和读取本地文件数据的
|
|
def handler(self,file_name,novel_name,data="",mode="a",encoding="utf-8",tag="source"):
|
|
if tag == "source":
|
|
file_dir = os.path.join(self.SOURCE_DIR,novel_name)
|
|
file_last = "html"
|
|
elif tag == "novel":
|
|
file_dir = os.path.join(self.NOVEL_DIR,novel_name)
|
|
file_last = "text"
|
|
else:
|
|
file_dir = self.SOURCE_DIR
|
|
file_last = ""
|
|
os.makedirs(file_dir,exist_ok=True)
|
|
file_path = os.path.join(file_dir,f"{file_name}.{file_last}")
|
|
if not os.path.exists(file_path):
|
|
with open(file=file_path, mode=mode, encoding=encoding) as fp:
|
|
if mode == "a" or mode == "w":
|
|
fp.write(data)
|
|
print(f"当前文件:",f"{file_name}.{file_last}","保存完成！")
|
|
else:
|
|
with open(file=file_path,mode=mode,encoding=encoding) as fp:
|
|
if mode == "a" or mode == "w":
|
|
fp.close()
|
|
print(f"当前文件:",f"{file_name}.{file_last}","已存在！")
|
|
else:
|
|
data = fp.read()
|
|
return data
|
|
# 抓取小说主页
|
|
def spider_index(self):
|
|
# 定义目标地址
|
|
target_url = f"{self.area}/book/43278/"
|
|
page_text,tree = self.create_tree(target_url=target_url)
|
|
novel_name = tree.xpath('//div[@class="info"]/h1/text()')[0].strip()
|
|
# /html/body/div[5]/div[2]/div[2]
|
|
novel_info = tree.xpath('//div[@class="info"]/div[2]/span')
|
|
author_name = novel_info[0].xpath("./text()")[0]
|
|
is_close = novel_info[1].xpath("./text()")[0]
|
|
update_time = novel_info[2].xpath("./text()")[0]
|
|
last_update = f'最新:{novel_info[-1].xpath("./a/text()")[0]}({self.area + novel_info[-1].xpath("./a/@href")[0]})'
|
|
data = f'''
|
|
{novel_name}
|
|
{author_name}
|
|
{is_close}
|
|
{update_time}
|
|
{last_update}
|
|
'''
|
|
self.novel_name = novel_name
|
|
#print(data)
|
|
self.handler(file_name="index",novel_name=novel_name,data=page_text)
|
|
self.handler(file_name="index",novel_name=novel_name,data=data,tag="novel")
|
|
def spider_capter(self):
|
|
self.novel_name = "道诡异仙"
|
|
index_page_text = self.handler(file_name="index",novel_name=self.novel_name,mode="r",)
|
|
tree = etree.HTML(index_page_text)
|
|
# /html/body/div[5]
|
|
dd_list_hide = tree.xpath("/html/body/div[5]/dl/span/dd")
|
|
dd_list = tree.xpath("/html/body/div[5]/dl/dd")
|
|
dd_list.extend(dd_list_hide)
|
|
detail_url_list = []
|
|
for dd in dd_list:
|
|
detail_url = self.area + dd.xpath("./a/@href")[0]
|
|
detail_title = dd.xpath("./a/text()")[0]
|
|
if "dd_show" in detail_url:
|
|
pass
|
|
else:
|
|
print(detail_url)
|
|
#page_index,tree = self.create_tree(target_url="https://www.bqg726.xyz/#/book/55729/2.html")
|
|
#print(page_index)
|
|
#tree = self.create_tree(target_url="https://www.bqgie.cc/book/43278/5.html")
|
|
#print(tree)
|
|
#page_text,tree = self.create_tree(target_url=detail_url)
|
|
## self.handler(file_name=detail_title,novel_name=self.novel_name,data=page_text)
|
|
#print(page_text)
|
|
#print(tree)
|
|
def main(self):
|
|
self.spider_index()
|
|
self.spider_capter()
|
|
|
|
|
|
if __name__ == '__main__':
|
|
spider = SpiderBiQuGe()
|
|
spider.main()
|