laramies/theHarvester
1
1
Fork 0
mirror of https://github.com/laramies/theHarvester.git synced 2025-02-24 22:42:56 +08:00
Code Issues Projects Releases Packages Wiki Activity

Update RocketReach API query parameters and pagination logic

Browse source 
Revised the data query parameters to use 'current_employer_domain' instead of 'company_domain' and updated the pagination handling to align with the new API response structure. Enhanced exception logging to specify RocketReach as the source of the error.
This commit is contained in:
L1ghtn1ng 2024-10-26 19:27:49 +01:00
parent 4495dc8407
commit 0b0d6516b1
1 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
theHarvester/discovery/rocketreach.py
View file

@ -27,7 +27,7 @@ async def do_search(self) -> None:
next_page = 1 # track pagination
for count in range(1, self.limit):
data = f'{{"query":{{"company_domain": ["{self.word}"]}}, "start": {next_page}, "page_size": 100}}'
data = f'{{"query":{{"current_employer_domain": ["{self.word}"]}}, "page": {next_page}, "page_size": 100}}'
result = await AsyncFetcher.post_fetch(self.baseurl, headers=headers, data=data, json=True)
if 'detail' in result.keys() and 'error' in result.keys() and 'Subscribe to a plan to access' in result['detail']:
# No more results can be fetched
@ -46,14 +46,14 @@ async def do_search(self) -> None:
if 'linkedin_url' in dict(profile).keys():
self.links.add(profile['linkedin_url'])
if 'pagination' in dict(result).keys():
next_page = int(result['pagination']['next'])
if next_page > int(result['pagination']['total']):
next_page = result['pagination']['page'] + 1
if next_page > result['pagination']['total_pages']:
break
await asyncio.sleep(get_delay() + 5)
except Exception as e:
print(f'An exception has occurred: {e}')
print(f'An exception has occurred rocketreach: {e}')
async def get_links(self):
return self.links