bacow/AV_Data_Capture
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

bugfix

Browse Source
This commit is contained in:
lededev
2021-11-14 08:52:45 +08:00
parent 4d7aad19d0
commit 701cc954cb
5 changed files with 16 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
AV_Data_Capture.py
View File

@@ -474,18 +474,16 @@ def main():
check_update(version) check_update(version)
# Download Mapping Table, parallel version # Download Mapping Table, parallel version
down_map_tab = [] user_data_home = Path.home() / '.local' / 'share' / 'avdc'
actor_xml = Path.home() / '.local' / 'share' / 'avdc' / 'mapping_actor.xml' map_tab = (
if not actor_xml.exists(): ('https://raw.githubusercontent.com/yoshiko2/AV_Data_Capture/master/MappingTable/mapping_actor.xml',
down_map_tab.append(( user_data_home / 'mapping_actor.xml'),
"https://raw.githubusercontent.com/yoshiko2/AV_Data_Capture/master/MappingTable/mapping_actor.xml", ('https://raw.githubusercontent.com/yoshiko2/AV_Data_Capture/master/MappingTable/mapping_info.xml',
actor_xml)) user_data_home / 'mapping_info.xml'),
info_xml = Path.home() / '.local' / 'share' / 'avdc' / 'mapping_info.xml' ('https://raw.githubusercontent.com/yoshiko2/AV_Data_Capture/master/MappingTable/c_number.json',
if not info_xml.exists(): user_data_home / 'c_number.json')
down_map_tab.append(( )
"https://raw.githubusercontent.com/yoshiko2/AV_Data_Capture/master/MappingTable/mapping_info.xml", res = parallel_download_files(((k, v) for k, v in map_tab if not v.exists()))
info_xml))
res = parallel_download_files(down_map_tab)
for i, fp in enumerate(res, start=1): for i, fp in enumerate(res, start=1):
if fp and len(fp): if fp and len(fp):
print(f"[+] [{i}/{len(res)}] Mapping Table Downloaded to {fp}") print(f"[+] [{i}/{len(res)}] Mapping Table Downloaded to {fp}")

4
WebCrawler/avsox.py
View File

@@ -57,8 +57,8 @@ def getCover_small(html):
result = str(html.xpath('//*[@id="waterfall"]/div/a/div[1]/img/@src')).strip(" ['']") result = str(html.xpath('//*[@id="waterfall"]/div/a/div[1]/img/@src')).strip(" ['']")
return result return result
def getTag(html): def getTag(html):
result = html.xpath('/html/head/meta[@name="keywords"]/@content')[0].split(',') x = html.xpath('/html/head/meta[@name="keywords"]/@content')[0].split(',')
return result return [i.strip() for i in x[2:]] if len(x) > 2 else []
def getSeries(html): def getSeries(html):
try: try:
result1 = str(html.xpath('//span[contains(text(),"系列:")]/../span[2]/text()')).strip(" ['']") result1 = str(html.xpath('//span[contains(text(),"系列:")]/../span[2]/text()')).strip(" ['']")

2
WebCrawler/fc2.py
View File

@@ -14,7 +14,7 @@ def getTitle_fc2com(htmlcode): #获取厂商
return result return result
def getActor_fc2com(htmlcode): def getActor_fc2com(htmlcode):
try: try:
htmtml = etree.fromstring(htmlcode, etree.HTMLParser()) html = etree.fromstring(htmlcode, etree.HTMLParser())
result = html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/ul/li[3]/a/text()')[0] result = html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/ul/li[3]/a/text()')[0]
return result return result
except: except:

2
WebCrawler/javbus.py
View File

@@ -72,7 +72,7 @@ def getSerise(html): #获取系列
return str(x[0]) if len(x) else '' return str(x[0]) if len(x) else ''
def getTag(html): # 获取标签 def getTag(html): # 获取标签
klist = html.xpath('/html/head/meta[@name="keywords"]/@content')[0].split(',') klist = html.xpath('/html/head/meta[@name="keywords"]/@content')[0].split(',')
return klist return [v for v in klist[1:]]
def getExtrafanart(htmlcode): # 获取剧照 def getExtrafanart(htmlcode): # 获取剧照
html_pather = re.compile(r'<div id=\"sample-waterfall\">[\s\S]*?</div></a>\s*?</div>') html_pather = re.compile(r'<div id=\"sample-waterfall\">[\s\S]*?</div></a>\s*?</div>')
html = html_pather.search(htmlcode) html = html_pather.search(htmlcode)