def get_single_role(div, summary):
"""
Scrape details of a single role
Args:
div: the div element
summary: the summary section
Returns:
A dict of the details for a single role
"""
title = summary.find_element_by_css_selector('.t-16.t-black.t-bold').text
company = summary.find_element_by_class_name('pv-entity__secondary-title').text
dates = get_span_text(summary, '.pv-entity__date-range.t-14.t-black--light.t-normal')
location = get_optional_text(summary, '.pv-entity__location.t-14.t-black--light.t-normal.block')
description = get_description(div, '.pv-entity__description.t-14.t-black.t-normal.ember-view')
results = {
NAME: company,
ENTRIES: [{
TITLE: title,
DATES: dates,
LOCATION: location,
DESCRIPTION: description
}]
}
return results
def get_projects(ul):
"""
Scrape projects details
Args:
ul: the ul element
Returns:
A list of details of all projects
"""
projects = []
for li in ul.find_elements_by_tag_name('li'):
name = li.find_element_by_class_name('pv-accomplishment-entity__title').text.replace('Project name', '').strip()
dates = get_optional_text(li, '.pv-accomplishment-entity__date.pv-accomplishment-entity__subtitle',
is_span=False)
description = get_description(li, '.pv-accomplishment-entity__description.t-14.t-black--light.t-normal').\
lstrip('Project description\n')
link = get_accomplishment_link(li)
projects.append({
NAME: name,
DATES: dates,
DESCRIPTION: description,
LINK: link
})
return projects
def get_volunteering(section):
"""
Scrape volunteering details
Args:
section: the volunteering section
Returns:
A list of details of all volunteering
"""
ul = get_section(section)
vol_dict = defaultdict(list)
for li in ul.find_elements_by_tag_name('li'):
title = li.find_element_by_css_selector('.t-16.t-black.t-bold').text
organisation = get_span_text(li, '.t-14.t-black.t-normal')
dates = get_optional_text(
li, '.pv-entity__date-range.detail-facet.inline-block.t-14.t-black--light.t-normal')
description = get_description(li, '.pv-entity__description.t-14.t-black--light.t-normal.mt4')
vol_dict[organisation].append({
TITLE: title,
DATES: dates,
LOCATION: '',
DESCRIPTION: description
})
vol_list = []
for organisation in vol_dict:
vol_list.append({
NAME: organisation,
ENTRIES: vol_dict[organisation]
})
return vol_list
def get_projects(ul):
"""
Scrape projects details
Args:
ul: the ul element
Returns:
A list of details of all projects
"""
projects = []
for li in ul.find_elements_by_tag_name("li"):
name = (li.find_element_by_class_name(
"pv-accomplishment-entity__title").text.replace(
"Project name", "").strip())
dates = get_optional_text(
li,
".pv-accomplishment-entity__date.pv-accomplishment-entity__subtitle",
is_span=False,
)
description = get_description(
li, ".pv-accomplishment-entity__description.t-14").lstrip(
"Project description\n")
link = get_accomplishment_link(li)
projects.append({
NAME: name,
DATES: dates,
DESCRIPTION: description,
LINK: link
})
return projects
def get_multiple_roles(div, summary):
"""
Scrape details of multiple roles
Args:
div: the div element
summary: the summary section
Returns:
A dict of the details for multiple roles
"""
company = get_span_text(summary, '.t-16.t-black.t-bold')
# Show all roles
try:
div.find_element_by_css_selector(
'.pv-profile-section__see-more-inline.pv-profile-section__text-truncate-toggle.link'
).click()
time.sleep(1)
except NoSuchElementException:
pass
roles = []
try:
role_sections = div.find_elements_by_class_name(
'pv-entity__position-group-role-item')
except NoSuchElementException:
role_sections = div.find_elements_by_class_name(
'pv-entity__position-group-role-item-fading-timeline')
for role_section in role_sections:
title = get_span_text(role_section, '.t-14.t-black.t-bold')
dates = get_span_text(role_section,
'.pv-entity__date-range.t-14.t-black.t-normal')
location = get_optional_text(
role_section,
'.pv-entity__location.t-14.t-black--light.t-normal.block')
description = get_description(
role_section,
'.pv-entity__description.t-14.t-black.t-normal.ember-view')
roles.append({
TITLE: title,
DATES: dates,
LOCATION: location,
DESCRIPTION: description
})
results = {NAME: company, ENTRIES: roles}
return results
def get_education(section):
"""
Scrape education details
Args:
section: the education section
Returns:
A list of details of all educations
"""
# The ul element can appear in two different classes
try:
ul = section.find_element_by_css_selector(
'.pv-profile-section__section-info.section-info.pv-profile-section__section-info--has-no-more.ember-view'
)
except NoSuchElementException:
ul = section.find_element_by_css_selector(
'.pv-profile-section__section-info.section-info.pv-profile-section__section-info--has-no-more'
)
edu_dict = defaultdict(list)
for li in ul.find_elements_by_tag_name('li'):
school = li.find_element_by_css_selector(
'.pv-entity__school-name.t-16.t-black.t-bold').text
degree_name = get_span_text(
li,
'.pv-entity__secondary-title.pv-entity__degree-name.pv-entity__secondary-title.t-14.t-black.t-normal'
)
dates = get_optional_text(
li, '.pv-entity__dates.t-14.t-black--light.t-normal')
description = get_description(
li, '.pv-entity__description.t-14.t-black--light.t-normal.mt4')
edu_dict[school].append({
DEGREE: get_degree(li, degree_name),
LOCATION: '',
DATES: dates,
DESCRIPTION: description
})
edu_list = []
for school in edu_dict:
edu_list.append({NAME: school, ENTRIES: edu_dict[school]})
return edu_list
def get_multiple_roles(div, summary):
"""
Scrape details of multiple roles
Args:
div: the div element
summary: the summary section
Returns:
A dict of the details for multiple roles
"""
try:
role_sections = div.find_elements_by_class_name(
"pv-entity__position-group-role-item")
except NoSuchElementException:
role_sections = div.find_elements_by_class_name(
"pv-entity__position-group-role-item-fading-timeline")
roles = []
for role_section in role_sections:
title = get_span_text(role_section, ".t-14.t-black.t-bold")
dates = get_span_text(role_section,
".pv-entity__date-range.t-14.t-black.t-normal")
location = get_optional_text(
role_section,
".pv-entity__location.t-14.t-black--light.t-normal.block")
description = get_description(
role_section,
".pv-entity__description.t-14.t-black.t-normal.ember-view")
roles.append({
TITLE: title,
DATES: dates,
LOCATION: location,
DESCRIPTION: description
})
results = {
NAME: get_span_text(summary, ".t-16.t-black.t-bold"),
ENTRIES: roles
}
return results
def get_education(section):
"""
Scrape education details
Args:
section: the education section
Returns:
A list of details of all educations
"""
ul = get_section(section)
edu_dict = defaultdict(list)
for li in ul.find_elements_by_tag_name('li'):
school = li.find_element_by_css_selector(
'.pv-entity__school-name.t-16.t-black.t-bold').text
degree_name = get_span_text(
li,
'.pv-entity__secondary-title.pv-entity__degree-name.pv-entity__secondary-title.t-14.t-black.t-normal'
)
dates = get_optional_text(
li, '.pv-entity__dates.t-14.t-black--light.t-normal')
description = get_description(
li, '.pv-entity__description.t-14.t-black--light.t-normal.mt4')
# Check if there is a degree name, if not, skip this entry
if not degree_name:
continue
edu_dict[school].append({
DEGREE: get_degree(li, degree_name),
LOCATION: '',
DATES: dates,
DESCRIPTION: description
})
edu_list = []
for school in edu_dict:
edu_list.append({NAME: school, ENTRIES: edu_dict[school]})
return edu_list
