gavin/kman
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

kindle manager

Browse Source
This commit is contained in:
gavin
2020-06-14 18:35:55 +08:00
parent 85fc992180
commit 854d167d20
1 changed files with 9 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
tbook.py → parseweb.py
View File

@@ -1,8 +1,10 @@
######################################################### #########################################################
## @file : tbook.py ## @file : parseweb.py
## @desc : douban book spide ## @desc : douban and amazon book spide
## @create : 2020/6/13 ## amazon ASIN B07VKS1DRZ - https://www.amazon.cn/s?k=B07VKS1DRZ
## douban SID 25742200 - https://book.douban.com/subject/25742200
## @create : 2020/6/14
## @author : Chengan ## @author : Chengan
## @email : douboer@gmail.com ## @email : douboer@gmail.com
######################################################### #########################################################
@@ -126,7 +128,7 @@ div class="result">
</div> </div>
</div>""" </div>"""
class doubanSpide(): class bookInfoSpide():
""" """
re_bn = re.compile(r''' re_bn = re.compile(r'''
@@ -154,12 +156,11 @@ class doubanSpide():
#re_end = re.compile(r'''<\/body><\/html>''') #re_end = re.compile(r'''<\/body><\/html>''')
re_end = re.compile(r'''^<span class=\"a-letter-space\"><\/span><\/div><\/div>''') re_end = re.compile(r'''^<span class=\"a-letter-space\"><\/span><\/div><\/div>''')
#amazon ASIN B07VKS1DRZ - https://www.amazon.cn/s?k=B07VKS1DRZ
def __init__(self): def __init__(self):
pass pass
def parse_books(self, mbkn: str): def grab_book_info(self, mbkn: str):
"""mbkn - bookname to be spided """mbkn - bookname to be spided
return: { return: {
"25853071": { # sid "25853071": { # sid
@@ -315,12 +316,12 @@ class doubanSpide():
if __name__ == '__main__': if __name__ == '__main__':
spide = doubanSpide() spide = bookInfoSpide()
for bkname in testbooks: for bkname in testbooks:
bkname = re.split(r'[\(（\-\:：_\s]',bkname.strip())[0] bkname = re.split(r'[\(（\-\:：_\s]',bkname.strip())[0]
print(bkname) print(bkname)
bkinfo = spide.parse_books(bkname) bkinfo = spide.grab_book_info(bkname)
filter_bkinfo = spide.filter_spide_books(bkname, bkinfo) filter_bkinfo = spide.filter_spide_books(bkname, bkinfo)
logger.debug('================ {} ================'.format(bkname)) logger.debug('================ {} ================'.format(bkname))