cwx/ComicScrapy
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

fix

Browse Source
This commit is contained in:
caiwx86 2024-03-31 19:38:40 +08:00
parent 7499cd78c7
commit e61ab9173b
2 changed files with 40 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
Comics/spiders/baseSpider.py Normal file
View File

@ -0,0 +1,28 @@
import logging, os
from Comics.utils import Conf
from Comics.utils import ComicPath
from Comics.loader import ComicLoader
from Comics.items import ComicItem
class baseSpider:
def parse_comic_data(self, project, response):
data = []
# 初始化Comic数据并根据工程名称读取配置文件并自动解析
comic_item = Conf().comic(project, ComicLoader(ComicItem(), response))
# 循环遍历根据配置文件自动解析并注入的章节名和章节链接
for chapter, link in zip(comic_item.get_chapters(), comic_item.get_chapter_href()):
# 打包导出item数据
item = comic_item.load_item(chapter=chapter)
# 获取最终存放CBZ的路径
cbz_path = ComicPath(item=item).PATH_CBZ()
# 校验繁体和简体中文CBZ路径是否存在
# if not checkUtils().is_error(item) and os.path.exists(cbz_path):
if cbz_path !=None and os.path.exists(cbz_path):
logging.info(f"漫画 {cbz_path} 已存在, 跳过中...")
data.append({ "success" : False, "item" : item})
else:
# 开始访问章节链接并跳转到self.parse_chapter
# yield scrapy.Request(self.main_url+link, meta={'item': item}, callback=self.parse_chapter)
data.append({ "success" : True, "item" : item, "link" : link})
return data

36
Comics/spiders/rm_comic.py
View File

@ -1,10 +1,10 @@
import scrapy,logging,time,os,skip
from Comics.items import ComicItem
from Comics.loader import ComicLoader
from Comics.utils import ComicPath
from Comics.spiders.baseSpider import baseSpider
from Comics.utils import Conf
class RmComicSpider(scrapy.Spider):
class RmComicSpider(scrapy.Spider, baseSpider):
name = 'rm_comic'
allowed_domains = ['roum12.xyz']
main_url = 'https://'+allowed_domains[0]
@ -27,32 +27,21 @@ class RmComicSpider(scrapy.Spider):
# 获取某个漫画的相关数据
# 获取到多个章节链接后进入下个流程
def parse_comic(self, response):
# 初始化Comic数据并根据工程名称读取配置文件并自动解析
comic_item = Conf().comic(self.name, ComicLoader(ComicItem(), response))
# 循环遍历根据配置文件自动解析并注入的章节名和章节链接
for chapter, link in zip(comic_item.get_chapters(), comic_item.get_chapter_href()):
# 打包导出item数据
item = comic_item.load_item(chapter=chapter)
# 获取最终存放CBZ的路径
cbz_path = ComicPath(item=item).PATH_CBZ()
# 校验繁体和简体中文CBZ路径是否存在
# if not checkUtils().is_error(item) and os.path.exists(cbz_path):
if cbz_path !=None and os.path.exists(cbz_path):
logging.info(f"漫画 {cbz_path} 已存在, 跳过中...")
yield item
else:
for comic in super().parse_comic_data(self.name, response):
if comic.get("success"):
# 开始访问章节链接并跳转到self.parse_chapter
yield scrapy.Request(self.main_url+link, meta={'item': item}, callback=self.parse_chapter)
yield scrapy.Request(self.main_url+comic.get("link"), meta={'item': comic.get("item")}, callback=self.parse_chapter)
else:
yield comic.get("item")
# 读取某章节下的所有图片
def parse_chapter(self, response):
# 获取传入的漫画item数据
comic_item = ComicLoader(item=response.meta['item'], response=response)
data = comic_item.get_xpath('//script[@id="__NEXT_DATA__"]/text()')[0]
item: ComicLoader = Conf().parse_chapter(item=comic_item, value=data)
comic = item.load_item()
chapter_api_url = item.get_chapter_api()
ci = ComicLoader(item=response.meta['item'], response=response)
# 再次通过获取的XPATH数据解析并保存到ci(ComicItem)中
item: ComicLoader = Conf().parse_chapter(item=ci, value=ci.get_xpath('//script[@id="__NEXT_DATA__"]/text()')[0])
comic, chapter_api_url = [ item.load_item() ,item.get_chapter_api() ]
if chapter_api_url is not None and len(chapter_api_url) != 0 :
try:
yield scrapy.Request(self.main_url + chapter_api_url, meta={'item': comic}, callback=self.parse_chapter_api)
@ -64,8 +53,7 @@ class RmComicSpider(scrapy.Spider):
# 加密数据API处理
def parse_chapter_api(self, response):
comic_item = ComicLoader(item=response.meta['item'], response=response)
item: ComicLoader = Conf().parse_chapter_api(item=comic_item, value=response.text)
yield item.load_item()
return Conf().parse_chapter_api(item=comic_item, value=response.text).load_item()
def parse(self, response):