This commit is contained in:
dece 2021-03-15 20:12:02 +01:00
commit fb43e28c6e
2 changed files with 139 additions and 0 deletions

59
build-form-list.py Normal file
View file

@ -0,0 +1,59 @@
import string
import sys
import time
import requests
from bs4 import BeautifulSoup
BASE_URL = "https://www.cnrtl.fr"
PER_FIRST_LETTER_URL = BASE_URL + "/portailindex/LEXI/TLFI/"
def main():
for letter in string.ascii_uppercase:
try:
with open(f"lexical_forms_{letter}.txt", "wt") as letter_file:
process_letter(letter, letter_file)
except OSError as exc:
exit(f"FUCK {exc}")
def process_letter(letter, letter_file):
next_url = PER_FIRST_LETTER_URL + letter
while True:
print(f"Processing {next_url}")
response = requests.get(next_url)
if response.status_code != 200:
exit(f"ERROR {response.status_code} at {next_url}")
next_page = process_page(response.text, letter_file)
if not next_page:
break
next_url = BASE_URL + next_page
def process_page(page, output):
soup = BeautifulSoup(page, "html.parser")
hometab = soup.find("table", class_="hometab")
lexical_forms = [td.string for td in hometab("td")]
for form in lexical_forms:
if form:
output.write(str(form) + "\n")
nav_table = hometab.find_next_sibling("table")
if not nav_table:
return None
nav_table_cells = nav_table("td")
if not nav_table_cells or len(nav_table_cells) < 2:
return None
second_cell = nav_table_cells[1]
next_page_link = second_cell.find("a")
if not next_page_link:
return None
try:
return next_page_link["href"]
except KeyError:
return None
if __name__ == "__main__":
main()

80
get_definitions.py Normal file
View file

@ -0,0 +1,80 @@
import os
import sys
import urllib.parse
from pathlib import Path
import requests
from bs4 import BeautifulSoup
from requests import models
BASE_URL = "https://www.cnrtl.fr/definition/"
def main():
forms_list_filepath = sys.argv[1]
start_from = ""
if len(sys.argv) > 2:
start_from = sys.argv[2]
try:
with open(forms_list_filepath, "rt") as forms_list_file:
for form in forms_list_file:
form = form.rstrip()
if start_from:
if start_from != form:
continue
else:
start_from = ""
get_definitions(form)
except OSError:
exit("Could not open forms list file.")
def get_definitions(form):
url = BASE_URL + urllib.parse.quote(form)
print(f"Processing {url}")
content = get_page(url)
soup = BeautifulSoup(content, "html.parser")
process_definition_page(soup, form, 0)
# Check other definitions.
tabs_bar = soup.find("div", id="vtoolbar")
if not tabs_bar:
sys.stderr.write("No tabs bar!\n")
return
num_defs = len(tabs_bar("li"))
for variant in range(1, num_defs): # skip the first, we got it above.
variant_url = url + f"/{variant}"
print(f"Processing {variant_url}")
content = get_page(variant_url)
soup = BeautifulSoup(content, "html.parser")
process_definition_page(soup, form, variant)
def get_page(url):
response = requests.get(url)
if response.status_code != 200:
sys.stderr.write(f"ERROR {response.status_code} at {url}\n")
return response.text
def process_definition_page(soup, form, variant):
definition = soup.find("div", id="lexicontent")
if not definition:
sys.stderr.write("No definition!\n")
return
save_definition(form, variant, definition.prettify())
def save_definition(name, variant, content):
def_dir = Path.cwd() / name
def_dir.mkdir(exist_ok=True)
def_file_path = def_dir / f"{variant}.txt"
try:
with open(def_file_path, "wt") as def_file:
def_file.write(content)
except OSError as exc:
sys.stderr.write(f"Could not save definition at {def_file_path}: {exc}")
if __name__ == "__main__":
main()