def get_page(self, name: str):
name = self.special_chars_to_hex(name, [" ", "'", "&"])
name = name.split(' (')[0]
return make_soup(
f'https://www.reuters.com/search/news?sortBy=&dateRange=&blob={name}'
)
def click_links(self, links):
for i, link in enumerate(links):
print("Parsing page: {}".format(i))
if i not in [4, 22, 24, 29, 38, 49, 50, 63, 73, 88, 89, 105, 109]:
page_soup = make_soup(
f'http://www.chambers-associate.com{link}')
self.parse_individual_page(page_soup)
def __init__(self):
self._firms = []
self._soup = make_soup(self.main_url)
def click_link(self):
self._page += 1
self._soup = make_soup(
f"https://www.ilrg.com/nlj250?page={self._page}")
self.parse_page(self._soup)
def get_page(self, name: str):
name = super().special_chars_to_hex(name, [" ", "'", "&"])
name = name.split(' (')[0]
return make_soup(f'https://abovethelaw.com/?s={name}')