def scrap_out_thumbs(dom):
"""Scrap out thumbnail data from <script> tags.
"""
ret_val = {}
thumb_name = 'vidthumb'
for script in eval_xpath_list(dom,
'//script[contains(., "_setImagesSrc")]'):
_script = script.text
# var s='data:image/jpeg;base64, ...'
_imgdata = _re("s='([^']*)").findall(_script)
if not _imgdata:
continue
# var ii=['vidthumb4','vidthumb7']
for _vidthumb in _re(r"(%s\d+)" % thumb_name).findall(_script):
# At least the equal sign in the URL needs to be decoded
ret_val[_vidthumb] = _imgdata[0].replace(r"\x3d", "=")
# {google.ldidly=-1;google.ldi={"vidthumb8":"https://...
for script in eval_xpath_list(dom,
'//script[contains(., "google.ldi={")]'):
_script = script.text
for key_val in _re(r'"%s\d+\":\"[^\"]*"' %
thumb_name).findall(_script):
match = _re(r'"(%s\d+)":"(.*)"' % thumb_name).search(key_val)
if match:
# At least the equal sign in the URL needs to be decoded
ret_val[match.group(1)] = match.group(2).replace(
r"\u003d", "=")
logger.debug("found %s imgdata for: %s", thumb_name, ret_val.keys())
return ret_val
def response(resp):
resp_url = urlparse(resp.url)
if resp_url.path.startswith('/verify'):
raise SearxEngineAccessDeniedException()
results = []
dom = html.fromstring(resp.content.decode())
for result_element in eval_xpath_list(dom, '//div[@id="searchpage-root"]//div[@data-dot="results"]/div'):
dot_data = eval_xpath_getindex(result_element, './div/div[@data-dot-data]/@data-dot-data', 0, default=None)
if dot_data is None:
title_element = eval_xpath_getindex(result_element, './/h3/a', 0)
results.append({
'url': title_element.get('href'),
'title': extract_text(title_element),
'content': extract_text(eval_xpath_getindex(title_element, '../../div[2]', 0)),
})
elif dot_data == '{"reporter_name":"hint/related/relates"}':
suggestions_element = eval_xpath_getindex(result_element,
'./div/div[@data-dot="main-box"]', 0, default=None)
if suggestions_element is not None:
for suggestion in eval_xpath_list(suggestions_element, './/ul/li'):
results.append({'suggestion': extract_text(suggestion)})
return results
def response(resp):
results = []
dom = html.fromstring(resp.text)
for result in eval_xpath_list(dom, '//div[contains(@class,"algo-sr")]'):
url = eval_xpath_getindex(result, './/h3/a/@href', 0, default=None)
if url is None:
continue
url = parse_url(url)
title = eval_xpath_getindex(result, './/h3/a', 0, default=None)
if title is None:
continue
offset = len(extract_text(title.xpath('span')))
title = extract_text(title)[offset:]
content = eval_xpath_getindex(
result, './/div[contains(@class, "compText")]', 0, default=''
)
if content:
content = extract_text(content)
# append result
results.append({'url': url,
'title': title,
'content': content})
for suggestion in eval_xpath_list(dom, '//div[contains(@class, "AlsoTry")]'):
# append suggestion
results.append({'suggestion': extract_text(suggestion)})
return results
def response(resp):
"""Get response from google's search request"""
results = []
detect_google_sorry(resp)
# convert the text to dom
dom = html.fromstring(resp.text)
vidthumb_imgdata = scrap_out_thumbs(dom)
# parse results
for result in eval_xpath_list(dom, results_xpath):
# google *sections*
if extract_text(eval_xpath(result, g_section_with_header)):
logger.debug("ingoring <g-section-with-header>")
continue
title = extract_text(eval_xpath_getindex(result, title_xpath, 0))
url = eval_xpath_getindex(result, href_xpath, 0)
c_node = eval_xpath_getindex(result, content_xpath, 0)
# <img id="vidthumb1" ...>
img_id = eval_xpath_getindex(c_node,
'./div[1]//a/g-img/img/@id',
0,
default=None)
if img_id is None:
continue
img_src = vidthumb_imgdata.get(img_id, None)
if not img_src:
logger.error("no vidthumb imgdata for: %s" % img_id)
img_src = eval_xpath_getindex(c_node, './div[1]//a/g-img/img/@src',
0)
length = extract_text(eval_xpath(c_node, './/div[1]//a/div[3]'))
content = extract_text(eval_xpath(c_node, './/div[2]/span'))
pub_info = extract_text(eval_xpath(c_node, './/div[2]/div'))
results.append({
'url': url,
'title': title,
'content': content,
'length': length,
'author': pub_info,
'thumbnail': img_src,
'template': 'videos.html',
})
# parse suggestion
for suggestion in eval_xpath_list(dom, suggestion_xpath):
# append suggestion
results.append({'suggestion': extract_text(suggestion)})
for correction in eval_xpath_list(dom, spelling_suggestion_xpath):
results.append({'correction': extract_text(correction)})
return results
def test_eval_xpath_list(self):
doc = html.fromstring(TestXPathUtils.TEST_DOC)
# check a not empty list
self.assertEqual(utils.eval_xpath_list(doc, '//i/text()'), ['italic'])
# check min_len parameter
with self.assertRaises(SearxEngineXPathException) as context:
utils.eval_xpath_list(doc, '//p', min_len=1)
self.assertEqual(context.exception.message, 'len(xpath_str) < 1')
self.assertEqual(context.exception.xpath_str, '//p')
def response(resp):
results = []
dom = html.fromstring(resp.text)
for result in eval_xpath_list(
dom, '//table[contains(@class, "table-list")]/tbody//tr'):
href = urljoin(
url,
eval_xpath_getindex(result,
'./td[contains(@class, "name")]/a[2]/@href',
0))
title = extract_text(
eval_xpath(result, './td[contains(@class, "name")]/a[2]'))
seed = extract_text(
eval_xpath(result, './/td[contains(@class, "seeds")]'))
leech = extract_text(
eval_xpath(result, './/td[contains(@class, "leeches")]'))
filesize_info = extract_text(
eval_xpath(result, './/td[contains(@class, "size")]/text()'))
filesize, filesize_multiplier = filesize_info.split()
filesize = get_torrent_size(filesize, filesize_multiplier)
results.append({
'url': href,
'title': title,
'seed': seed,
'leech': leech,
'filesize': filesize,
'template': 'torrent.html'
})
return results
def response(resp):
'''post-response callback
resp: requests response object
'''
results = []
dom = html.fromstring(resp.text)
number_of_results_element =\
eval_xpath_getindex(dom, '//a[@class="active" and contains(@href,"/suchen/dudenonline")]/span/text()',
0, default=None)
if number_of_results_element is not None:
number_of_results_string = re.sub('[^0-9]', '',
number_of_results_element)
results.append({'number_of_results': int(number_of_results_string)})
for result in eval_xpath_list(dom,
'//section[not(contains(@class, "essay"))]'):
url = eval_xpath_getindex(result, './/h2/a', 0).get('href')
url = urljoin(base_url, url)
title = eval_xpath(result, 'string(.//h2/a)').strip()
content = extract_text(eval_xpath(result, './/p'))
# append result
results.append({'url': url, 'title': title, 'content': content})
return results
def response(resp):
if resp.url.path.startswith('/verify'):
raise SearxEngineAccessDeniedException()
results = []
dom = html.fromstring(resp.content.decode())
for result_element in eval_xpath_list(dom,
'//div[@data-dot="results"]/div'):
result_data = eval_xpath_getindex(result_element,
'.//div[contains(@class, "bec586")]',
0,
default=None)
if result_data is None:
continue
title_element = eval_xpath_getindex(result_element, './/h3/a', 0)
results.append({
'url':
title_element.get('href'),
'title':
extract_text(title_element),
'content':
extract_text(eval_xpath(result_data, './/div[@class="_3eded7"]')),
})
return results
def response(resp):
results = []
dom = html.fromstring(resp.text)
# parse results
for result in eval_xpath_list(dom, '//div[@class="g"]'):
title = extract_text(eval_xpath(result, './/h3'))
url = eval_xpath_getindex(result, './/div[@class="r"]/a/@href', 0)
content = extract_text(eval_xpath(result, './/span[@class="st"]'))
# get thumbnails
script = str(dom.xpath('//script[contains(., "_setImagesSrc")]')[0].text)
ids = result.xpath('.//div[@class="s"]//img/@id')
if len(ids) > 0:
thumbnails_data = \
re.findall('s=\'(.*?)(?:\\\\[a-z,1-9,\\\\]+\'|\')\;var ii=\[(?:|[\'vidthumb\d+\',]+)\'' + ids[0],
script)
tmp = []
if len(thumbnails_data) != 0:
tmp = re.findall('(data:image/jpeg;base64,[a-z,A-Z,0-9,/,\+]+)', thumbnails_data[0])
thumbnail = ''
if len(tmp) != 0:
thumbnail = tmp[-1]
# append result
results.append({'url': url,
'title': title,
'content': content,
'thumbnail': thumbnail,
'template': 'videos.html'})
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 _fetch_supported_languages(resp):
supported_languages = []
dom = html.fromstring(resp.text)
offset = len('lang_')
for val in eval_xpath_list(dom, '//div[contains(@class, "lang-item")]/input/@value'):
supported_languages.append(val[offset:])
return supported_languages
def _fetch_supported_languages(resp):
ret_val = {}
dom = html.fromstring(resp.text)
radio_buttons = eval_xpath_list(dom, '//*[@id="langSec"]//input[@name="lr"]')
for x in radio_buttons:
name = x.get("data-name")
code = x.get("value").split('_')[-1]
ret_val[code] = {"name": name}
return ret_val
def request(query, params):
response_index = get(base_url, headers=params['headers'], raise_for_httperror=True)
dom = html.fromstring(response_index.text)
url_params = {'q': query}
for e in eval_xpath_list(dom, '//input[@type="hidden"]'):
name = e.get('name')
value = e.get('value')
url_params[name] = value
params['url'] = base_url + '?' + urlencode(url_params)
params['cookies'] = response_index.cookies
return params
def response(resp):
results = []
dom = html.fromstring(resp.text)
for result in eval_xpath_list(dom, results_xpath):
single_result = {'template': template}
for single_field in field_definition:
single_field = {**default_field_settings, **single_field}
try:
if single_field['single_element']:
node = eval_xpath(result, single_field['xpath'])
else:
node = eval_xpath_list(result, single_field['xpath'])
if 'extract' in single_field and single_field[
'extract'] == 'url':
value = extract_url(node, search_url)
elif 'extract' in single_field and single_field[
'extract'] == 'boolean':
value = (isinstance(node, list) and len(node) > 0)
elif 'extract' in single_field and single_field[
'extract'] == 'boolean_negate':
value = (isinstance(node, list) and len(node) < 1)
else:
value = extract_text(node)
single_result[single_field['field_name']] = value
except Exception as e:
logger.warning('error in resolving field %s:\n%s',
single_field['field_name'], e)
single_result[single_field['field_name']] = unresolvable_value
results.append(single_result)
return results
def response(resp):
"""Get response from google's search request"""
results = []
detect_google_sorry(resp)
# which subdomain ?
# subdomain = resp.search_params.get('google_subdomain')
# convert the text to dom
dom = html.fromstring(resp.text)
# parse results
for result in eval_xpath_list(dom, '//div[@class="gs_ri"]'):
title = extract_text(eval_xpath(result, './h3[1]//a'))
if not title:
# this is a [ZITATION] block
continue
url = eval_xpath(result, './h3[1]//a/@href')[0]
content = extract_text(eval_xpath(result, './div[@class="gs_rs"]')) or ''
pub_info = extract_text(eval_xpath(result, './div[@class="gs_a"]'))
if pub_info:
content += "[%s]" % pub_info
pub_type = extract_text(eval_xpath(result, './/span[@class="gs_ct1"]'))
if pub_type:
title = title + " " + pub_type
results.append({
'url': url,
'title': title,
'content': content,
})
# parse suggestion
for suggestion in eval_xpath(dom, '//div[contains(@class, "gs_qsuggest_wrap")]//li//a'):
# append suggestion
results.append({'suggestion': extract_text(suggestion)})
for correction in eval_xpath(dom, '//div[@class="gs_r gs_pda"]/a'):
results.append({'correction': extract_text(correction)})
return results
def response(resp):
# get the base URL for the language in which request was made
base_url = lang_urls["all"]["base"]
results = []
dom = html.fromstring(resp.text)
# parse results
for result in eval_xpath_list(dom, xpath_results):
link = eval_xpath_getindex(result, xpath_link, 0)
href = urljoin(base_url, link.attrib.get("href"))
title = extract_text(link)
results.append({"url": href, "title": title})
return results
def response(resp):
# get the base URL for the language in which request was made
language = locale_to_lang_code(resp.search_params['language'])
base_url = get_lang_urls(language)['base']
results = []
dom = html.fromstring(resp.text)
# parse results
for result in eval_xpath_list(dom, xpath_results):
link = eval_xpath_getindex(result, xpath_link, 0)
href = urljoin(base_url, link.attrib.get('href'))
title = extract_text(link)
results.append({'url': href, 'title': title})
return results
def response(resp):
results = []
dom = html.fromstring(resp.content)
for entry in eval_xpath_list(dom, '//entry'):
title = eval_xpath_getindex(entry, './/title', 0).text
url = eval_xpath_getindex(entry, './/id', 0).text
content_string = '{doi_content}{abstract_content}'
abstract = eval_xpath_getindex(entry, './/summary', 0).text
# If a doi is available, add it to the snipppet
doi_element = eval_xpath_getindex(entry,
'.//link[@title="doi"]',
0,
default=None)
doi_content = doi_element.text if doi_element is not None else ''
content = content_string.format(doi_content=doi_content,
abstract_content=abstract)
if len(content) > 300:
content = content[0:300] + "..."
# TODO: center snippet on query term
publishedDate = datetime.strptime(
eval_xpath_getindex(entry, './/published', 0).text,
'%Y-%m-%dT%H:%M:%SZ')
res_dict = {
'url': url,
'title': title,
'publishedDate': publishedDate,
'content': content
}
results.append(res_dict)
return results
def response(resp):
results = []
dom = html.fromstring(resp.text)
# parse results
for result in eval_xpath_list(
dom,
"//div[@id='content']//div[@class='listWidget']/div/div[@class='appRow']"
):
link = eval_xpath_getindex(result, './/h5/a', 0)
url = base_url + link.attrib.get('href') + '#downloads'
title = extract_text(link)
img_src = base_url + eval_xpath_getindex(result, './/img/@src', 0)
res = {'url': url, 'title': title, 'img_src': img_src}
results.append(res)
return results
def response(resp):
results = []
dom = html.fromstring(resp.text)
for result in eval_xpath_list(dom, xpath_results):
# defaults
filesize = 0
magnet_link = "magnet:?xt=urn:btih:{}&tr=http://tracker.acgsou.com:2710/announce"
category = extract_text(
eval_xpath_getindex(result, xpath_category, 0, default=[]))
page_a = eval_xpath_getindex(result, xpath_title, 0)
title = extract_text(page_a)
href = base_url + page_a.attrib.get('href')
magnet_link = magnet_link.format(page_a.attrib.get('href')[5:-5])
filesize_info = eval_xpath_getindex(result,
xpath_filesize,
0,
default=None)
if filesize_info:
try:
filesize = filesize_info[:-2]
filesize_multiplier = filesize_info[-2:]
filesize = get_torrent_size(filesize, filesize_multiplier)
except:
pass
# I didn't add download/seed/leech count since as I figured out they are generated randomly everytime
content = 'Category: "{category}".'
content = content.format(category=category)
results.append({
'url': href,
'title': title,
'content': content,
'filesize': filesize,
'magnetlink': magnet_link,
'template': 'torrent.html'
})
return results
def response(resp):
results = []
dom = html.fromstring(resp.text)
# parse results
for result in eval_xpath_list(
dom,
'.//div[@id="content"]/div[@class="listWidget"]/div[@class="appRow"]'
):
link = eval_xpath_getindex(result, './/h5/a', 0)
url = base_url + link.attrib.get('href') + '#downloads'
title = extract_text(link)
thumbnail_src = base_url\
+ eval_xpath_getindex(result, './/img', 0).attrib.get('src').replace('&w=32&h=32', '&w=64&h=64')
res = {'url': url, 'title': title, 'thumbnail_src': thumbnail_src}
# append result
results.append(res)
# return results
return results
def response(resp):
results = []
xmldom = etree.fromstring(resp.content)
xmlsearchresult = eval_xpath_getindex(xmldom, '//searchresult', 0)
dom = html.fragment_fromstring(xmlsearchresult.text, create_parent='div')
for link in eval_xpath_list(dom, '/div/table/tr/td/div[2]//a'):
url = urljoin(base_url, link.attrib.get('href'))
title = extract_text(link)
thumbnail_src = urljoin(
gallery_url,
eval_xpath_getindex(link, './/img', 0).attrib['src'])
# append result
results.append({
'url': url,
'title': title,
'img_src': thumbnail_src,
'content': '',
'thumbnail_src': thumbnail_src,
'template': 'images.html'
})
# return results
return results
def response(resp):
"""Get response from google's search request"""
results = []
detect_google_sorry(resp)
# convert the text to dom
dom = html.fromstring(resp.text)
img_bas64_map = scrap_out_thumbs(dom)
img_src_script = eval_xpath_getindex(
dom, '//script[contains(., "AF_initDataCallback({key: ")]', 1).text
# parse results
#
# root element::
# <div id="islmp" ..>
# result div per image::
# <div jsmodel="tTXmib"> / <div jsaction="..." data-id="..."
# The data-id matches to a item in a json-data structure in::
# <script nonce="I+vqelcy/01CKiBJi5Z1Ow">AF_initDataCallback({key: 'ds:1', ... data:function(){return [ ...
# In this structure the link to the origin PNG, JPG or whatever is given
# first link per image-div contains a <img> with the data-iid for bas64 encoded image data::
# <img class="rg_i Q4LuWd" data-iid="0"
# second link per image-div is the target link::
# <a class="VFACy kGQAp" href="https://en.wikipedia.org/wiki/The_Sacrament_of_the_Last_Supper">
# the second link also contains two div tags with the *description* and *publisher*::
# <div class="WGvvNb">The Sacrament of the Last Supper ...</div>
# <div class="fxgdke">en.wikipedia.org</div>
root = eval_xpath(dom, '//div[@id="islmp"]')
if not root:
logger.error("did not find root element id='islmp'")
return results
root = root[0]
for img_node in eval_xpath_list(root, './/img[contains(@class, "rg_i")]'):
img_alt = eval_xpath_getindex(img_node, '@alt', 0)
img_base64_id = eval_xpath(img_node, '@data-iid')
if img_base64_id:
img_base64_id = img_base64_id[0]
thumbnail_src = img_bas64_map[img_base64_id]
else:
thumbnail_src = eval_xpath(img_node, '@src')
if not thumbnail_src:
thumbnail_src = eval_xpath(img_node, '@data-src')
if thumbnail_src:
thumbnail_src = thumbnail_src[0]
else:
thumbnail_src = ''
link_node = eval_xpath_getindex(img_node, '../../../a[2]', 0)
url = eval_xpath_getindex(link_node, '@href', 0)
pub_nodes = eval_xpath(link_node, './div/div')
pub_descr = img_alt
pub_source = ''
if pub_nodes:
pub_descr = extract_text(pub_nodes[0])
pub_source = extract_text(pub_nodes[1])
img_src_id = eval_xpath_getindex(img_node, '../../../@data-id', 0)
src_url = scrap_img_by_id(img_src_script, img_src_id)
if not src_url:
src_url = thumbnail_src
results.append({
'url': url,
'title': img_alt,
'content': pub_descr,
'source': pub_source,
'img_src': src_url,
# 'img_format': img_format,
'thumbnail_src': thumbnail_src,
'template': 'images.html'
})
return results
def response(resp):
"""Get response from google's search request"""
results = []
detect_google_sorry(resp)
# which subdomain ?
# subdomain = resp.search_params.get('google_subdomain')
# convert the text to dom
dom = html.fromstring(resp.text)
for result in eval_xpath_list(dom, '//div[@class="xrnccd"]'):
# The first <a> tag in the <article> contains the link to the
# article The href attribute of the <a> is a google internal link,
# we can't use. The real link is hidden in the jslog attribute:
#
# <a ...
# jslog="95014; 4:https://www.cnn.com/.../index.html; track:click"
# href="./articles/CAIiENu3nGS...?hl=en-US&gl=US&ceid=US%3Aen"
# ... />
jslog = eval_xpath_getindex(result, './article/a/@jslog', 0)
url = re.findall('http[^;]*', jslog)
if url:
url = url[0]
else:
# The real URL is base64 encoded in the json attribute:
# jslog="95014; 5:W251bGwsbnVsbCxudW...giXQ==; track:click"
jslog = jslog.split(";")[1].split(':')[1].strip()
try:
padding = (4 -(len(jslog) % 4)) * "="
jslog = b64decode(jslog + padding)
except binascii.Error:
# URL cant be read, skip this result
continue
# now we have : b'[null, ... null,"https://www.cnn.com/.../index.html"]'
url = re.findall('http[^;"]*', str(jslog))[0]
# the first <h3> tag in the <article> contains the title of the link
title = extract_text(eval_xpath(result, './article/h3[1]'))
# the first <div> tag in the <article> contains the content of the link
content = extract_text(eval_xpath(result, './article/div[1]'))
# the second <div> tag contains origin publisher and the publishing date
pub_date = extract_text(eval_xpath(result, './article/div[2]//time'))
pub_origin = extract_text(eval_xpath(result, './article/div[2]//a'))
pub_info = []
if pub_origin:
pub_info.append(pub_origin)
if pub_date:
# The pub_date is mostly a string like 'yesertday', not a real
# timezone date or time. Therefore we can't use publishedDate.
pub_info.append(pub_date)
pub_info = ', '.join(pub_info)
if pub_info:
content = pub_info + ': ' + content
# The image URL is located in a preceding sibling <img> tag, e.g.:
# "https://lh3.googleusercontent.com/DjhQh7DMszk.....z=-p-h100-w100"
# These URL are long but not personalized (double checked via tor).
img_src = extract_text(result.xpath('preceding-sibling::a/figure/img/@src'))
results.append({
'url': url,
'title': title,
'content': content,
'img_src': img_src,
})
# return results
return results
def response(resp):
"""Get response from google's search request"""
detect_google_sorry(resp)
results = []
# which subdomain ?
# subdomain = resp.search_params.get('google_subdomain')
# convert the text to dom
dom = html.fromstring(resp.text)
# results --> answer
answer = eval_xpath(dom, '//div[contains(@class, "LGOjhe")]//text()')
if answer:
results.append({'answer': ' '.join(answer)})
else:
logger.debug("did not found 'answer'")
# results --> number_of_results
try:
_txt = eval_xpath_getindex(dom,
'//div[@id="result-stats"]//text()', 0)
_digit = ''.join([n for n in _txt if n.isdigit()])
number_of_results = int(_digit)
results.append({'number_of_results': number_of_results})
except Exception as e: # pylint: disable=broad-except
logger.debug("did not 'number_of_results'")
logger.error(e, exc_info=True)
# parse results
for result in eval_xpath_list(dom, results_xpath):
# google *sections*
if extract_text(eval_xpath(result, g_section_with_header)):
logger.debug("ingoring <g-section-with-header>")
continue
try:
title_tag = eval_xpath_getindex(result,
title_xpath,
0,
default=None)
if title_tag is None:
# this not one of the common google results *section*
logger.debug(
'ingoring <div class="g" ../> section: missing title')
continue
title = extract_text(title_tag)
url = eval_xpath_getindex(result, href_xpath, 0)
content = extract_text(eval_xpath_getindex(result,
content_xpath,
0,
default=None),
allow_none=True)
results.append({'url': url, 'title': title, 'content': content})
except Exception as e: # pylint: disable=broad-except
logger.error(e, exc_info=True)
# from lxml import etree
# logger.debug(etree.tostring(result, pretty_print=True))
# import pdb
# pdb.set_trace()
continue
# parse suggestion
for suggestion in eval_xpath_list(dom, suggestion_xpath):
# append suggestion
results.append({'suggestion': extract_text(suggestion)})
for correction in eval_xpath_list(dom, spelling_suggestion_xpath):
results.append({'correction': extract_text(correction)})
# return results
return results
def response(resp):
'''Scrap *results* from the response (see :ref:`engine results`).
'''
results = []
dom = html.fromstring(resp.text)
is_onion = 'onions' in categories # pylint: disable=undefined-variable
if results_xpath:
for result in eval_xpath_list(dom, results_xpath):
url = extract_url(eval_xpath_list(result, url_xpath, min_len=1),
search_url)
title = extract_text(
eval_xpath_list(result, title_xpath, min_len=1))
content = extract_text(
eval_xpath_list(result, content_xpath, min_len=1))
tmp_result = {'url': url, 'title': title, 'content': content}
# add thumbnail if available
if thumbnail_xpath:
thumbnail_xpath_result = eval_xpath_list(
result, thumbnail_xpath)
if len(thumbnail_xpath_result) > 0:
tmp_result['img_src'] = extract_url(
thumbnail_xpath_result, search_url)
# add alternative cached url if available
if cached_xpath:
tmp_result['cached_url'] = (cached_url + extract_text(
eval_xpath_list(result, cached_xpath, min_len=1)))
if is_onion:
tmp_result['is_onion'] = True
results.append(tmp_result)
else:
if cached_xpath:
for url, title, content, cached in zip(
(extract_url(x, search_url)
for x in eval_xpath_list(dom, url_xpath)),
map(extract_text, eval_xpath_list(dom, title_xpath)),
map(extract_text, eval_xpath_list(dom, content_xpath)),
map(extract_text, eval_xpath_list(dom, cached_xpath))):
results.append({
'url': url,
'title': title,
'content': content,
'cached_url': cached_url + cached,
'is_onion': is_onion
})
else:
for url, title, content in zip(
(extract_url(x, search_url)
for x in eval_xpath_list(dom, url_xpath)),
map(extract_text, eval_xpath_list(dom, title_xpath)),
map(extract_text, eval_xpath_list(dom, content_xpath))):
results.append({
'url': url,
'title': title,
'content': content,
'is_onion': is_onion
})
if suggestion_xpath:
for suggestion in eval_xpath(dom, suggestion_xpath):
results.append({'suggestion': extract_text(suggestion)})
logger.debug("found %s results", len(results))
return results
def response(resp):
results = []
dom = html.fromstring(resp.text)
is_onion = True if 'onions' in categories else False
if results_xpath:
for result in eval_xpath_list(dom, results_xpath):
url = extract_url(eval_xpath_list(result, url_xpath, min_len=1),
search_url)
title = extract_text(
eval_xpath_list(result, title_xpath, min_len=1))
content = extract_text(
eval_xpath_list(result, content_xpath, min_len=1))
tmp_result = {'url': url, 'title': title, 'content': content}
# add thumbnail if available
if thumbnail_xpath:
thumbnail_xpath_result = eval_xpath_list(
result, thumbnail_xpath)
if len(thumbnail_xpath_result) > 0:
tmp_result['img_src'] = extract_url(
thumbnail_xpath_result, search_url)
# add alternative cached url if available
if cached_xpath:
tmp_result['cached_url'] = cached_url\
+ extract_text(eval_xpath_list(result, cached_xpath, min_len=1))
if is_onion:
tmp_result['is_onion'] = True
results.append(tmp_result)
else:
if cached_xpath:
for url, title, content, cached in zip(
(extract_url(x, search_url)
for x in eval_xpath_list(dom, url_xpath)),
map(extract_text, eval_xpath_list(dom, title_xpath)),
map(extract_text, eval_xpath_list(dom, content_xpath)),
map(extract_text, eval_xpath_list(dom, cached_xpath))):
results.append({
'url': url,
'title': title,
'content': content,
'cached_url': cached_url + cached,
'is_onion': is_onion
})
else:
for url, title, content in zip(
(extract_url(x, search_url)
for x in eval_xpath_list(dom, url_xpath)),
map(extract_text, eval_xpath_list(dom, title_xpath)),
map(extract_text, eval_xpath_list(dom, content_xpath))):
results.append({
'url': url,
'title': title,
'content': content,
'is_onion': is_onion
})
if not suggestion_xpath:
return results
for suggestion in eval_xpath(dom, suggestion_xpath):
results.append({'suggestion': extract_text(suggestion)})
return results
def response(resp):
"""Get response from google's search request"""
detect_google_sorry(resp)
results = []
# convert the text to dom
dom = html.fromstring(resp.text)
# results --> answer
answer_list = eval_xpath(dom, '//div[contains(@class, "LGOjhe")]')
if answer_list:
answer_list = [_.xpath("normalize-space()") for _ in answer_list]
results.append({'answer': ' '.join(answer_list)})
else:
logger.debug("did not find 'answer'")
# results --> number_of_results
if not use_mobile_ui:
try:
_txt = eval_xpath_getindex(
dom, '//div[@id="result-stats"]//text()', 0)
_digit = ''.join([n for n in _txt if n.isdigit()])
number_of_results = int(_digit)
results.append({'number_of_results': number_of_results})
except Exception as e: # pylint: disable=broad-except
logger.debug("did not 'number_of_results'")
logger.error(e, exc_info=True)
# parse results
_results_xpath = results_xpath
if use_mobile_ui:
_results_xpath = results_xpath_mobile_ui
for result in eval_xpath_list(dom, _results_xpath):
# google *sections*
if extract_text(eval_xpath(result, g_section_with_header)):
logger.debug("ingoring <g-section-with-header>")
continue
try:
title_tag = eval_xpath_getindex(result,
title_xpath,
0,
default=None)
if title_tag is None:
# this not one of the common google results *section*
logger.debug(
'ingoring item from the result_xpath list: missing title')
continue
title = extract_text(title_tag)
url = eval_xpath_getindex(result, href_xpath, 0, None)
if url is None:
continue
content = extract_text(eval_xpath_getindex(result,
content_xpath,
0,
default=None),
allow_none=True)
if content is None:
logger.debug(
'ingoring item from the result_xpath list: missing content of title "%s"',
title)
continue
logger.debug('add link to results: %s', title)
results.append({'url': url, 'title': title, 'content': content})
except Exception as e: # pylint: disable=broad-except
logger.error(e, exc_info=True)
continue
# parse suggestion
for suggestion in eval_xpath_list(dom, suggestion_xpath):
# append suggestion
results.append({'suggestion': extract_text(suggestion)})
for correction in eval_xpath_list(dom, spelling_suggestion_xpath):
results.append({'correction': extract_text(correction)})
# return results
return results
