def test_parser_find_all_divs_with_specific_attrs():
# 21 elements represents the real results + the one row of localized results
h = ParseHTML(SALARIES)
attrs = {'class': 'dataRow first'}
tag = 'tr'
res = [ele for ele in h.find_all(tag, attrs)]
assert(len(res) == 21)
def parse_salaries_data(data, tag="tbody", class_type="dataRow"):
data = ParseHTML(data)
for row in data.find_all(tag):
tr = row.tr
if not tr.has_key("class"):
continue
if tr["class"].find(class_type) == -1:
continue
yield tr
def parse_jobs_data(data, tag="div", class_type="jobListing"):
data = ParseHTML(data)
for row in data.find_all(tag):
if not row.has_key("class"):
continue
this_class = row["class"].split(" ")
if not class_type in this_class:
continue
yield row
def test_parser_find_all_elements():
h = ParseHTML(SALARIES)
res = [ele for ele in h.find_all('div')]
assert(len(res) == 260)
def test_parser_find_all_elements():
h = ParseHTML(SALARIES)
res = [ele for ele in h.find_all(True)]
assert(len(res) == 1054)