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

fix lxml unicode handling

Browse source
This commit is contained in:
j 2013-07-04 20:32:54 +02:00
parent b1d248c4df
commit ad7e21e7a8
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
ox/web/twitter.py
View file

@ -11,13 +11,13 @@ from ox.cache import read_url
def find(query, timeout=60): def find(query, timeout=60):
url = 'https://twitter.com/search/' + quote(query) url = 'https://twitter.com/search/' + quote(query)
data = ox.cache.read_url(url, timeout=timeout) data = ox.cache.read_url(url, timeout=timeout).decode('utf-8')
doc = lxml.html.document_fromstring(data) doc = lxml.html.document_fromstring(data)
tweets = [] tweets = []
for e in doc.xpath("//div[contains(@class, 'original-tweet')]"): for e in doc.xpath("//div[contains(@class, 'original-tweet')]"):
t = lxml.html.tostring(e) t = lxml.html.tostring(e)
text = e.xpath(".//p[contains(@class, 'js-tweet-text')]")[0] text = e.xpath(".//p[contains(@class, 'js-tweet-text')]")[0]
html = lxml.html.tostring(text).strip() html = lxml.html.tostring(text, encoding='unicode').strip()
text = ox.decode_html(ox.strip_tags(html)).strip() text = ox.decode_html(ox.strip_tags(html)).strip()
user = re.compile('data-name="(.*?)"').findall(t)[0] user = re.compile('data-name="(.*?)"').findall(t)[0]
user = ox.decode_html(ox.strip_tags(user)).strip() user = ox.decode_html(ox.strip_tags(user)).strip()