zcy
/
zhihu_spider
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

div content crawler

master
ZouJiu 2023-10-20 20:51:29 +08:00
parent 469efcc0ce
commit b89f9a70e3
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
crawler.py
View File

@ -404,6 +404,8 @@ def parser_beautiful(innerHTML, article, number, dircrea, bk=False):
if len(prenode) > 0: if len(prenode) > 0:
for i in prenode: for i in prenode:
article += "\n\n```\n" + i.text + "\n```\n\n" article += "\n\n```\n" + i.text + "\n```\n\n"
else:
article, number = parser_beautiful(chi, article, number, dircrea, bk)
if bk: if bk:
article += "**" article += "**"
return article, number return article, number