0x2620/python-ox
2
1
Fork 0
Code Issues Pull requests Releases Wiki Activity

replace all CammelCase with under_score in ox

Browse source
This commit is contained in:
j 2012-08-14 16:12:43 +02:00
commit bb35daa95c
31 changed files with 242 additions and 244 deletions
Download patch file Download diff file Expand all files Collapse all files

16
ox/web/amazon.py
View file

@ -3,7 +3,7 @@
import re
from urllib import quote
from ox import findRe, strip_tags, decodeHtml
from ox import find_re, strip_tags, decode_html
from ox.cache import read_url
@ -12,7 +12,7 @@ def findISBN(title, author):
url = "http://www.amazon.com/s/ref=nb_sb_noss?url=search-alias%3Dstripbooks&field-keywords=" + "%s&x=0&y=0" % quote(q)
data = read_url(url, unicode=True)
links = re.compile('href="(http://www.amazon.com/.*?/dp/.*?)"').findall(data)
id = findRe(re.compile('href="(http://www.amazon.com/.*?/dp/.*?)"').findall(data)[0], '/dp/(.*?)/')
id = find_re(re.compile('href="(http://www.amazon.com/.*?/dp/.*?)"').findall(data)[0], '/dp/(.*?)/')
data = getData(id)
if author in data['authors']:
return data
@ -24,13 +24,13 @@ def getData(id):
def findData(key):
return findRe(data, '<li><b>%s:</b>(.*?)</li>'% key).strip()
return find_re(data, '<li><b>%s:</b>(.*?)</li>'% key).strip()
r = {}
r['amazon'] = url
r['title'] = findRe(data, '<span id="btAsinTitle" style="">(.*?)<span')
r['title'] = find_re(data, '<span id="btAsinTitle" style="">(.*?)<span')
r['authors'] = re.compile('<b class="h3color">(.*?)</b>.*?\(Author\)', re.DOTALL).findall(data)
r['authors'] = filter(lambda x: len(x)>1, [decodeHtml(a) for a in r['authors']])
r['authors'] = filter(lambda x: len(x)>1, [decode_html(a) for a in r['authors']])
t = re.compile('>(.*?)</a> \(Translator\)').findall(data)
if t:
r['translator'] = t
@ -38,15 +38,15 @@ def getData(id):
r['language'] = findData('Language')
r['isbn-10'] = findData('ISBN-10')
r['isbn-13'] = findData('ISBN-13').replace('-', '')
r['dimensions'] = findRe(data, '<li><b>.*?Product Dimensions:.*?</b>(.*?)</li>')
r['dimensions'] = find_re(data, '<li><b>.*?Product Dimensions:.*?</b>(.*?)</li>')
r['pages'] = findData('Paperback')
if not r['pages']:
r['pages'] = findData('Hardcover')
r['review'] = strip_tags(findRe(data, '<h3 class="productDescriptionSource">Review</h3>.*?<div class="productDescriptionWrapper">(.*?)</div>').replace('<br />', '\n')).strip()
r['review'] = strip_tags(find_re(data, '<h3 class="productDescriptionSource">Review</h3>.*?<div class="productDescriptionWrapper">(.*?)</div>').replace('<br />', '\n')).strip()
r['description'] = strip_tags(findRe(data, '<h3 class="productDescriptionSource">Product Description</h3>.*?<div class="productDescriptionWrapper">(.*?)</div>').replace('<br />', '\n')).strip()
r['description'] = strip_tags(find_re(data, '<h3 class="productDescriptionSource">Product Description</h3>.*?<div class="productDescriptionWrapper">(.*?)</div>').replace('<br />', '\n')).strip()
r['cover'] = re.findall('src="(.*?)" id="prodImage"', data)
if r['cover']: