def test_parse_url(self):
test_url = 'http://r.search.yahoo.com/_ylt=A0LEb9JUSKcAEGRXNyoA;_ylu=X3oDMTEzZm1qazYwBHNlYwNzcgRwb3MDMQRjb' +\
'2xvA2Jm2dGlkA1NNRTcwM18x/RV=2/RE=1423106085/RO=10/RU=https%3a%2f%2fthis.is.the.url%2f/RK=0/RS=' +\
'dtcJsfP4mEeBOjnVfUQ-'
url = yahoo.parse_url(test_url)
self.assertEqual('https://this.is.the.url/', url)
test_url = 'http://r.search.yahoo.com/_ylt=A0LElb9JUSKcAEGRXNyoA;_ylu=X3oDMTEzZm1qazYwBHNlYwNzcgRwb3MDMQRjb' +\
'2xvA2Jm2dGlkA1NNRTcwM18x/RV=2/RE=1423106085/RO=10/RU=https%3a%2f%2fthis.is.the.url%2f/RS=' +\
'dtcJsfP4mEeBOjnVfUQ-'
url = yahoo.parse_url(test_url)
self.assertEqual('https://this.is.the.url/', url)
test_url = 'https://this.is.the.url/'
url = yahoo.parse_url(test_url)
self.assertEqual('https://this.is.the.url/', url)
def test_parse_url(self):
test_url = 'http://r.search.yahoo.com/_ylt=A0LEb9JUSKcAEGRXNyoA;_ylu=X3oDMTEzZm1qazYwBHNlYwNzcgRwb3MDMQRjb' +\
'2xvA2Jm2dGlkA1NNRTcwM18x/RV=2/RE=1423106085/RO=10/RU=https%3a%2f%2fthis.is.the.url%2f/RK=0/RS=' +\
'dtcJsfP4mEeBOjnVfUQ-'
url = yahoo.parse_url(test_url)
self.assertEqual('https://this.is.the.url/', url)
test_url = 'http://r.search.yahoo.com/_ylt=A0LElb9JUSKcAEGRXNyoA;_ylu=X3oDMTEzZm1qazYwBHNlYwNzcgRwb3MDMQRjb' +\
'2xvA2Jm2dGlkA1NNRTcwM18x/RV=2/RE=1423106085/RO=10/RU=https%3a%2f%2fthis.is.the.url%2f/RS=' +\
'dtcJsfP4mEeBOjnVfUQ-'
url = yahoo.parse_url(test_url)
self.assertEqual('https://this.is.the.url/', url)
test_url = 'https://this.is.the.url/'
url = yahoo.parse_url(test_url)
self.assertEqual('https://this.is.the.url/', url)
def response(resp):
results = []
dom = html.fromstring(resp.text)
# parse results
for result in dom.xpath(results_xpath):
urls = result.xpath(url_xpath)
if len(urls) != 1:
continue
url = sanitize_url(parse_url(extract_url(urls, search_url)))
title = extract_text(result.xpath(title_xpath)[0])
content = extract_text(result.xpath(content_xpath)[0])
# parse publishedDate
publishedDate = extract_text(result.xpath(publishedDate_xpath)[0])
# still useful ?
if re.match("^[0-9]+ minute(s|) ago$", publishedDate):
publishedDate = datetime.now() - timedelta(
minutes=int(re.match(r'\d+', publishedDate).group()))
elif re.match("^[0-9]+ days? ago$", publishedDate):
publishedDate = datetime.now() - timedelta(
days=int(re.match(r'\d+', publishedDate).group()))
elif re.match("^[0-9]+ hour(s|), [0-9]+ minute(s|) ago$",
publishedDate):
timeNumbers = re.findall(r'\d+', publishedDate)
publishedDate = datetime.now()\
- timedelta(hours=int(timeNumbers[0]))\
- timedelta(minutes=int(timeNumbers[1]))
else:
try:
publishedDate = parser.parse(publishedDate)
except:
publishedDate = datetime.now()
if publishedDate.year == 1900:
publishedDate = publishedDate.replace(year=datetime.now().year)
# append result
results.append({
'url': url,
'title': title,
'content': content,
'publishedDate': publishedDate
})
# return results
return results
def response(resp):
results = []
dom = html.fromstring(resp.text)
for result in dom.xpath(results_xpath):
url = parse_url(extract_url(result.xpath(url_xpath), search_url))
title = extract_text(result.xpath(title_xpath)[0])
content = extract_text(result.xpath(content_xpath)[0])
results.append({'url': url, 'title': title, 'content': content})
if not suggestion_xpath:
return results
for suggestion in dom.xpath(suggestion_xpath):
results.append({'suggestion': extract_text(suggestion)})
return results
def response(resp):
results = []
dom = html.fromstring(resp.text)
# parse results
for result in eval_xpath_list(
dom, '//ol[contains(@class,"searchCenterMiddle")]//li'):
url = eval_xpath_getindex(result, './/h4/a/@href', 0, None)
if url is None:
continue
url = parse_url(url)
title = extract_text(result.xpath('.//h4/a'))
content = extract_text(result.xpath('.//p'))
img_src = eval_xpath_getindex(result, './/img/@data-src', 0, None)
item = {
'url': url,
'title': title,
'content': content,
'img_src': img_src
}
pub_date = extract_text(
result.xpath('.//span[contains(@class,"s-time")]'))
ago = AGO_RE.search(pub_date)
if ago:
number = int(ago.group(1))
delta = AGO_TIMEDELTA[ago.group(2)]
pub_date = datetime.now() - delta * number
else:
try:
pub_date = parser.parse(pub_date)
except parser.ParserError:
pub_date = None
if pub_date is not None:
item['publishedDate'] = pub_date
results.append(item)
for suggestion in eval_xpath_list(
dom, '//div[contains(@class,"AlsoTry")]//td'):
results.append({'suggestion': extract_text(suggestion)})
return results
def response(resp):
results = []
dom = html.fromstring(resp.text)
# parse results
for result in dom.xpath(results_xpath):
urls = result.xpath(url_xpath)
if len(urls) != 1:
continue
url = sanitize_url(parse_url(extract_url(urls, search_url)))
title = extract_text(result.xpath(title_xpath)[0])
content = extract_text(result.xpath(content_xpath)[0])
# parse publishedDate
publishedDate = extract_text(result.xpath(publishedDate_xpath)[0])
# still useful ?
if re.match("^[0-9]+ minute(s|) ago$", publishedDate):
publishedDate = datetime.now() - timedelta(minutes=int(re.match(r'\d+', publishedDate).group()))
elif re.match("^[0-9]+ days? ago$", publishedDate):
publishedDate = datetime.now() - timedelta(days=int(re.match(r'\d+', publishedDate).group()))
elif re.match("^[0-9]+ hour(s|), [0-9]+ minute(s|) ago$", publishedDate):
timeNumbers = re.findall(r'\d+', publishedDate)
publishedDate = datetime.now()\
- timedelta(hours=int(timeNumbers[0]))\
- timedelta(minutes=int(timeNumbers[1]))
else:
try:
publishedDate = parser.parse(publishedDate)
except:
publishedDate = datetime.now()
if publishedDate.year == 1900:
publishedDate = publishedDate.replace(year=datetime.now().year)
# append result
results.append({'url': url,
'title': title,
'content': content,
'publishedDate': publishedDate})
# return results
return results
def response(resp):
results = []
dom = html.fromstring(resp.text)
for result in dom.xpath(results_xpath):
url = parse_url(extract_url(result.xpath(url_xpath), search_url))
title = extract_text(result.xpath(title_xpath)[0])
content = extract_text(result.xpath(content_xpath)[0])
publishedDate = extract_text(result.xpath(publishedDate_xpath)[0])
if re.match("^[0-9]+ minute(s|) ago$", publishedDate):
publishedDate = datetime.now() - timedelta(minutes=int(re.match(r'\d+', publishedDate).group())) # noqa
else:
if re.match("^[0-9]+ hour(s|), [0-9]+ minute(s|) ago$",
publishedDate):
timeNumbers = re.findall(r'\d+', publishedDate)
publishedDate = datetime.now()\
- timedelta(hours=int(timeNumbers[0]))\
- timedelta(minutes=int(timeNumbers[1]))
else:
# TODO year in string possible?
publishedDate = datetime.strptime(publishedDate,
"%b %d %H:%M%p")
if publishedDate.year == 1900:
publishedDate = publishedDate.replace(year=datetime.now().year)
results.append({'url': url,
'title': title,
'content': content,
'publishedDate': publishedDate})
if not suggestion_xpath:
return results
for suggestion in dom.xpath(suggestion_xpath):
results.append({'suggestion': extract_text(suggestion)})
return results
def response(resp):
results = []
dom = html.fromstring(resp.text)
for result in dom.xpath(results_xpath):
url = parse_url(extract_url(result.xpath(url_xpath), search_url))
title = extract_text(result.xpath(title_xpath)[0])
content = extract_text(result.xpath(content_xpath)[0])
publishedDate = extract_text(result.xpath(publishedDate_xpath)[0])
if re.match("^[0-9]+ minute(s|) ago$", publishedDate):
publishedDate = datetime.now() - timedelta(minutes=int(re.match(r'\d+', publishedDate).group())) # noqa
else:
if re.match("^[0-9]+ hour(s|), [0-9]+ minute(s|) ago$",
publishedDate):
timeNumbers = re.findall(r'\d+', publishedDate)
publishedDate = datetime.now()\
- timedelta(hours=int(timeNumbers[0]))\
- timedelta(minutes=int(timeNumbers[1]))
else:
publishedDate = parser.parse(publishedDate)
if publishedDate.year == 1900:
publishedDate = publishedDate.replace(year=datetime.now().year)
results.append({'url': url,
'title': title,
'content': content,
'publishedDate': publishedDate})
if not suggestion_xpath:
return results
for suggestion in dom.xpath(suggestion_xpath):
results.append({'suggestion': extract_text(suggestion)})
return results