user01/CollectMangaInfo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update DataClass.py, GetArc_Ehentai.py, and 3 more files...

Browse Source 
E-hentai Page Parse
DataClass added
This commit is contained in:
Lee Young Hoon
2024-04-05 21:51:36 +09:00
parent dbe5377d6f
commit 809748a73a
5 changed files with 202 additions and 192 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
DataClass.py Normal file
View File

@@ -0,0 +1,13 @@
class MangaMetaInfo:
def __init__(self, title, url, lang, manType, *tags):
self.title = title
self.url = url
self.lang = lang
self.manType = manType
self.tags = tags
pass
#series
#type
#languages
#tags

129
GetArc_Ehentai.py
View File

@@ -6,34 +6,19 @@ from selenium.common.exceptions import TimeoutException
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
class MangaMetaInfo:
def __init__(self, title, url, lang, manType, *tags):
self.title = title
self.url = url
self.lang = lang
self.manType = manType
self.tags = tags
pass
#series
#type
#languages
#tags
class MangaInfo:
listResult = [] listResult = []
def GetSearchResult(self, searchWord): def GetSearchResult(searchWord):
url = self.getSiteUrl() + searchWord print("E-hentai start")
#url = getSiteUrl() + searchWord
url = "https://e-hentai.org/"
driver = webdriver.Chrome() driver = webdriver.Chrome()
driver.get(url) driver.get(url)
# 웹페이지가 로드될 때까지 기다리기 # 웹페이지가 로드될 때까지 기다리기
try: try:
WebDriverWait(driver, 30).until( WebDriverWait(driver, 30).until(
EC.presence_of_element_located((By.CLASS_NAME, 'lillie')) EC.presence_of_element_located((By.CLASS_NAME, 'dp'))
) )
except TimeoutException: except TimeoutException:
print("페이지가 로드되지 않았거나 요소를 찾을 수 없습니다.") print("페이지가 로드되지 않았거나 요소를 찾을 수 없습니다.")
@@ -43,76 +28,88 @@ class MangaInfo:
strContent = driver.page_source strContent = driver.page_source
driver.quit() driver.quit()
self.parseMangaInfos(strContent) parseMangaInfos(strContent)
pass pass
# #
def getSiteUrl(self): def getSiteUrl():
strRet = "https://e-hentai.org/search.html?" strRet = "https://e-hentai.org/?f_search="
return strRet return strRet
# #
def parseMangaInfos(self, html_doc): def parseMangaInfos(html_doc):
# BeautifulSoup 객체 생성 # BeautifulSoup 객체 생성
soup = BeautifulSoup(html_doc, 'html.parser') soup = BeautifulSoup(html_doc, 'html.parser')
gallery_elements = soup.find_all(class_='gallery-content') gallery_table = soup.find('table', class_='itg gltc')
gls = gallery_table.find_all('tr')
for element in gallery_elements:
self.djParse(element)
def djParse(self, soup_element):
childs = soup_element.find_all(class_='dj')
for child in childs:
self.djtitleParse(child)
self.artistlistParse(child)
self.djDescParse(child)
idx = 1;
for gl in gls:
gl1cParse(gl)
gl2cParse(gl)
gl3cParse(gl)
print("\r\n") print("\r\n")
def djtitleParse(self, soup_element): # type
element = soup_element.find('h1', class_='lillie') def gl1cParse(soup_element):
title = element.text element = soup_element.find('td', class_='gl1c glcat')
a_tag = element.find('a') if element is None:
a_url = a_tag.get('href') return
print("title : " + title) man_type = element.find('div')
print("URl : " + a_url)
def artistlistParse(self, soup_element): print("type : " + man_type.text)
element = soup_element.find('div', class_='artist-list')
print("artists") # torrent
def gl2cParse(soup_element):
element = soup_element.find('td', class_='gl2c')
a_tags = element.find_all('a') if element is None:
for tag in a_tags: return
artist = tag.text
a_url = tag.get('href') trt_btn = element.find('div', class_='gldown')
print(" " + artist + " " + a_url) trt_url = trt_btn.find('a')
if trt_url:
url = trt_url.get('href')
print("torrent : " + url)
else:
print("torrent : none")
def djDescParse(self, soup_element): #
element = soup_element.find('table', class_='dj-desc') def gl3cParse(soup_element):
tb_rows = element.find_all('tr') element = soup_element.find('td', class_='gl3c glname')
for row in tb_rows:
tds = row.find_all('td') if element is None:
if 2 != len(tds): return
print("td get failed")
continue elemenr_url = element.find('a')
man_url = elemenr_url.get('href')
element_title = element.find('div', class_='glink')
man_title = element_title.text
print("title : " + man_title)
print("Url : " + man_url)
print("tags : ")
tags = element.find_all('div', class_='gt')
man_tags = []
for tag in tags:
man_tag = tag.get('title')
print(" " + man_tag)
man_tags.append(man_tag)
print(len(man_tags))
print(tds[0].text + " : ")
a_tags = tds[1].find_all('a')
for tag in a_tags:
tag_name = tag.text
tag_url = tag.get('href')
print(" " + tag_name + " " + tag_url)
pass pass

28
GetArc_Hitomi.py
View File

@@ -21,12 +21,10 @@ class MangaMetaInfo:
#tags #tags
class MangaInfo:
listResult = [] listResult = []
def GetSearchResult(self, searchWord): def GetSearchResult(searchWord):
url = self.getSiteUrl() + searchWord url = getSiteUrl() + searchWord
driver = webdriver.Chrome() driver = webdriver.Chrome()
driver.get(url) driver.get(url)
@@ -43,39 +41,39 @@ class MangaInfo:
strContent = driver.page_source strContent = driver.page_source
driver.quit() driver.quit()
self.parseMangaInfos(strContent) parseMangaInfos(strContent)
pass pass
# #
def getSiteUrl(self): def getSiteUrl():
strRet = "https://hitomi.la/search.html?" strRet = "https://hitomi.la/search.html?"
return strRet return strRet
# #
def parseMangaInfos(self, html_doc): def parseMangaInfos(html_doc):
# BeautifulSoup 객체 생성 # BeautifulSoup 객체 생성
soup = BeautifulSoup(html_doc, 'html.parser') soup = BeautifulSoup(html_doc, 'html.parser')
gallery_elements = soup.find_all(class_='gallery-content') gallery_elements = soup.find_all(class_='gallery-content')
for element in gallery_elements: for element in gallery_elements:
self.djParse(element) djParse(element)
def djParse(self, soup_element): def djParse(soup_element):
childs = soup_element.find_all(class_='dj') childs = soup_element.find_all(class_='dj')
for child in childs: for child in childs:
self.djtitleParse(child) djtitleParse(child)
self.artistlistParse(child) artistlistParse(child)
self.djDescParse(child) djDescParse(child)
print("\r\n") print("\r\n")
def djtitleParse(self, soup_element): def djtitleParse(soup_element):
element = soup_element.find('h1', class_='lillie') element = soup_element.find('h1', class_='lillie')
title = element.text title = element.text
@@ -85,7 +83,7 @@ class MangaInfo:
print("title : " + title) print("title : " + title)
print("URl : " + a_url) print("URl : " + a_url)
def artistlistParse(self, soup_element): def artistlistParse(soup_element):
element = soup_element.find('div', class_='artist-list') element = soup_element.find('div', class_='artist-list')
print("artists") print("artists")
@@ -97,7 +95,7 @@ class MangaInfo:
print(" " + artist + " " + a_url) print(" " + artist + " " + a_url)
def djDescParse(self, soup_element): def djDescParse(soup_element):
element = soup_element.find('table', class_='dj-desc') element = soup_element.find('table', class_='dj-desc')
tb_rows = element.find_all('tr') tb_rows = element.find_all('tr')
for row in tb_rows: for row in tb_rows:

2
StoreXLS.py
View File

@@ -9,7 +9,6 @@ xls_name = "mangaDB.xlsx"
list_MetaInfo = [] list_MetaInfo = []
# #
def GetCurrentTime(): def GetCurrentTime():
# 현재 시간을 구하고 구조체로 변환 # 현재 시간을 구하고 구조체로 변환
@@ -38,7 +37,6 @@ def GetCurrentTime():
# wb = Workbook() # wb = Workbook()
# print("xls Created") # print("xls Created")
# ws = wb.active # ws = wb.active
# # time, title, url, tags (comma) # # time, title, url, tags (comma)
# ws['A1'] = "Modified Time" # ws['A1'] = "Modified Time"

10
main.py
View File

@@ -1,8 +1,12 @@
import GetArc_Hitomi as gethitomi import GetArc_Hitomi as getHitomi
import GetArc_Ehentai as getEhentai
def main(): def main():
obj = gethitomi.MangaInfo() #getHitomi.GetSearchResult("trouble sweets")
obj.GetSearchResult("trouble sweets") getEhentai.GetSearchResult("artist%3A%22kotomi+yo-ji%24%22")
#artist:"kotomi yo-ji$"
#"artist%3A%22kotomi+yo-ji%24%22"
# For Main Loop # For Main Loop