I have a scrapy script I wrote to extract profiles from LinkedIn using proxy services. The proxy am using is scrapeops. I created a virtual environment and did pip install scrapeops-scrapy-proxy-sdk. I also added the proxy API to my scrapy project settings following the proxy rules of usage. When i run my scrapy script, it runs successfully with no error but returns empty result. Please what am i missing?
Here is my code
What I have tried:
class ProfilespiderSpider(CrawlSpider):
name = 'profilespider'
allowed_domains = ['www.linkedin.com']
start_urls = ['https://www.linkedin.com/in/reidhoffman?trk=people-guest_people_search-card']
rules = (
Rule(LinkExtractor(allow='public_jobs_people-search-bar_search-submit')),
Rule(LinkExtractor(allow='people-guest_people_search-card'), callback='parse_item'),
)
def parse_item(self, response):
item = {}
"""
Profile Summary
"""
item['name'] = response.css("div.top-card-layout__entity-info-container h1::text").get().strip()
item['description'] = response.css("div.top-card-layout__entity-info-container h2::text").get().strip()
try:
item['location'] = response.css('section.top-card-layout div.top-card__subline-item::text').get()
except:
item['location'] = response.css('section.top-card-layout span.top-card__subline-item::text').get().strip()
if 'followers' in item['location'] or 'connections' in item['location']:
item['location'] = ''
contacts = response.css("div.top-card-layout__entity-info-container span.top-card__subline-item::text").getall()
item['followers'] = contacts[0].replace('followers', '').strip()
item['connections'] = contacts[1].replace('connections', '').strip()
"""
About Section
"""
item['about'] = response.css(".summary p::text").getall()
"""
Experience Section
"""
item['experience'] = []
experience_blocks = response.css('li.experience-item')
for block in experience_blocks:
experience = {}
try:
experience['position'] = block.css('li.experience-item h3::text').get().strip()
except Exception as e:
experience['position'] = ''
try:
experience['organisation_profile'] = block.css('h4 a::attr(href)').get().split('?')[0]
except Exception as e:
print('No organisation profile found')
experience['organisation_profile'] = ''
try:
date_ranges = block.css('span.date-range time::text').getall()
if len(date_ranges) == 2:
experience['start_time'] = date_ranges[0]
experience['end_time'] = date_ranges[1]
experience['duration'] = block.css('span.date-range__duration::text').get()
elif len(date_ranges) == 1:
experience['start_time'] = date_ranges[0]
experience['end_time'] = 'present'
experience['duration'] = block.css('span.date-range__duration::text').get()
except Exception as e:
print('No dates')
experience['start_time'] = ''
experience['end_time'] = ''
experience['duration'] = ''
try:
experience['location'] = block.css('p.experience-item__location::text').get().strip()
except Exception as e:
print('No location')
experience['location'] = ''
try:
experience['description'] = block.css('p.show-more-less-text__text--more::text').get().strip()
except Exception as e:
try:
experience['description'] = block.css('p.show-more-less-text__text--less::text').get().strip()
except Exception as e:
print('no description found')
experience['description'] = ''
item['experience'].append(experience)
"""
Education Section
"""
item['education'] = []
education_groups = response.css('li.education__list-item')
for group in education_groups:
education = {}
education['university_link'] = group.css('h3 a::attr(href)').get().split('?')[0]
try:
degree_info = group.css('h4 span::text').getall()
if len(degree_info) == 2:
education['degree'] = degree_info[0]
education['faculty'] = degree_info[1]
else:
pass
except:
print('no degrees acquired')
try:
date_range = group.css('span.date-range time::text').getall()
if len(date_range) == 2:
education['start_date'] = date_range[0]
education['end_date'] = date_range[1]
else:
pass
except:
print('no degree dates')
try:
education['description'] = group.css('div.show-more-less-text p::text').get().strip()
except:
education['description'] = ''
item['education'].append(education)
"""
Skills Section
"""
item['skills'] = []
skills = {}
try:
skills = response.css('div.core-section-container__content li.skills__item')
skills['start_up'] = skills[1].css('li.skills__item a::text').get().strip()
skills['strategy'] = skills[3].css('li.skills__item a::text').get().strip()
skills['venture capital'] = skills[5].css('li.skills__item a::text').get().strip()
skills['Saas'] = skills[7].css('li::text').get().strip()
except:
pass
item['skills'].append(skills)
yield item
When I run scrapy crawl profilespider -o profiles.json on my cmd prompt, the json file 'profiles' comes back empty. Please do you know what am missing?
Here is my log from console
(venv) C:\Users\LP\Documents\python\ProfileTest\profilescraper>scrapy crawl profilespider -o profiles.json
2023-01-24 15:35:58 [scrapy.utils.log] INFO: Scrapy 2.7.1 started (bot: profilescraper)
2023-01-24 15:35:58 [scrapy.utils.log] INFO: Versions: lxml 4.9.2.0, libxml2 2.9.12, cssselect 1.2.0, parsel 1.7.0, w3lib 2.1.1, Twisted 22.10.0, Python 3.10.7 (tags/v3.10.7:6cc6b13, Sep 5 2022, 14:08:36) [MSC v.1933 64 bit (AMD64)], pyOpenSSL 23.0.0 (OpenSSL 3.0.7 1 Nov 2022), cryptography 39.0.0, Platform Windows-10-10.0.19044-SP0
2023-01-24 15:35:58 [scrapy.crawler] INFO: Overridden settings:
{'BOT_NAME': 'profilescraper',
'NEWSPIDER_MODULE': 'profilescraper.spiders',
'REQUEST_FINGERPRINTER_IMPLEMENTATION': '2.7',
'SPIDER_MODULES': ['profilescraper.spiders'],
'TWISTED_REACTOR':
'twisted.internet.asyncioreactor.AsyncioSelectorReactor'}
2023-01-24 15:35:58 [asyncio] DEBUG: Using selector: SelectSelector
2023-01-24 15:35:58 [scrapy.utils.log] DEBUG: Using reactor: twisted.internet.asyncioreactor.AsyncioSelectorReactor
2023-01-24 15:35:58 [scrapy.utils.log] DEBUG: Using asyncio event loop: asyncio.windows_events._WindowsSelectorEventLoop
2023-01-24 15:35:58 [scrapy.extensions.telnet] INFO: Telnet Password: d126f5d312c5e917
2023-01-24 15:35:59 [scrapy.middleware] INFO: Enabled extensions:
['scrapy.extensions.corestats.CoreStats',
'scrapy.extensions.telnet.TelnetConsole',
'scrapy.extensions.feedexport.FeedExporter',
'scrapy.extensions.logstats.LogStats']
2023-01-24 15:35:59 [scrapy.middleware] INFO: Enabled downloader middlewares:
['scrapy.downloadermiddlewares.httpauth.HttpAuthMiddleware'
'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware',
'scrapy.downloadermiddlewares.stats.DownloaderStats']
2023-01-24 15:35:59 [scrapy.middleware] INFO: Enabled spider middlewares:
['scrapy.spidermiddlewares.httperror.HttpErrorMiddleware',
'scrapy.spidermiddlewares.offsite.OffsiteMiddleware',
'scrapy.spidermiddlewares.referer.RefererMiddleware',
'scrapy.spidermiddlewares.urllength.UrlLengthMiddleware',
'scrapy.spidermiddlewares.depth.DepthMiddleware']
2023-01-24 15:35:59 [scrapy.middleware] INFO: Enabled item pipelines:
[]
2023-01-24 15:35:59 [scrapy.core.engine] INFO: Spider opened
2023-01-24 15:35:59 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
2023-01-24 15:35:59 [scrapy.extensions.telnet] INFO: Telnet console listening on 127.0.0.1:6023
2023-01-24 15:36:07 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://proxy.scrapeops.io/v1/?api_key=9c79a52d-f08d-4c45-b8d2-f51ec9a4e7a4&url=https%3A%2F%2Fwww.linkedin.com%2Fpub%2Fdir%3FfirstName%3Dreid%26lastName%3Dhoffman%26trk%3Dpublic_jobs_people-search-bar_search-submit> (referer: None)
2023-01-24 15:36:07 [scrapy.core.engine] INFO: Closing spider (finished)
2023-01-24 15:36:07 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
{'downloader/request_bytes': 405,
'downloader/request_count': 1,
'downloader/request_method_count/GET': 1,
'downloader/response_bytes': 323474,
'downloader/response_count': 1,
'downloader/response_status_count/200': 1,
'elapsed_time_seconds': 8.263713,
'finish_reason': 'finished',
'finish_time': datetime.datetime(2023, 1, 24, 14, 36, 7, 939751),
'log_count/DEBUG': 4,
'log_count/INFO': 10,
'response_received_count': 1,
'scheduler/dequeued': 2,
'scheduler/dequeued/memory': 2,
'scheduler/enqueued': 2,
'scheduler/enqueued/memory': 2,
'start_time': datetime.datetime(2023, 1, 24, 14, 35, 59, 676038)}
2023-01-24 15:36:07 [scrapy.core.engine] INFO: Spider closed (finished)