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

tweak fanza getCover()

Browse Source
This commit is contained in:
jnozsc 2020-03-04 15:25:33 -08:00
parent bedd76bc60
commit 3b85ebfa51
1 changed files with 11 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
fanza.py
View File

@ -115,17 +115,20 @@ def getTag(text):
def getCover(text, number): def getCover(text, number):
html = etree.fromstring(text, etree.HTMLParser()) html = etree.fromstring(text, etree.HTMLParser())
cover_number = number cover_number = number
if "_" in cover_number:
# fanza modify _ to \u0005f for image id
cover_number = cover_number.replace("_", r"\u005f")
try: try:
result = html.xpath('//*[@id="' + cover_number + '"]/@href')[0] result = html.xpath('//*[@id="' + cover_number + '"]/@href')[0]
except: except:
# (TODO) handle more edge case # sometimes fanza modify _ to \u0005f for image id
# print(html) if "_" in cover_number:
# raise exception here, same behavior as before cover_number = cover_number.replace("_", r"\u005f")
# people's major requirement is fetching the picture try:
raise ValueError("can not find image") result = html.xpath('//*[@id="' + cover_number + '"]/@href')[0]
except:
# (TODO) handle more edge case
# print(html)
# raise exception here, same behavior as before
# people's major requirement is fetching the picture
raise ValueError("can not find image")
return result return result