s444498/wko_anime-face-similarity
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

scrap n images depends on argv param

Browse Source
This commit is contained in:
Mateusz 2023-01-15 14:17:33 +01:00
parent a27a7e612a
commit 1f4a2d9dfc
1 changed files with 39 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
scrape_data.py
View File

@ -3,8 +3,12 @@ from bs4 import BeautifulSoup
from lxml import etree from lxml import etree
import os import os
import csv import csv
import sys
ROOT_URL = "https://myanimelist.net/character.php" if len(sys.argv) > 1:
IMG_N = int(sys.argv[1])
else:
IMG_N = 50
def get_page_xpath_result(url, xpath_str): def get_page_xpath_result(url, xpath_str):
HEADERS = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'} HEADERS = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
@ -19,6 +23,12 @@ def createDirectory(path):
os.makedirs(path) os.makedirs(path)
print(f"The {path} is created!") print(f"The {path} is created!")
n = IMG_N // 50
for i in range(n):
ROOT_URL = f'https://myanimelist.net/character.php?limit={(i)*50}'
print(ROOT_URL)
character_links = get_page_xpath_result(ROOT_URL, '//div[@class="information di-ib mt24"]/a/@href') character_links = get_page_xpath_result(ROOT_URL, '//div[@class="information di-ib mt24"]/a/@href')
character_names = get_page_xpath_result(ROOT_URL, '//div[@class="information di-ib mt24"]/a') character_names = get_page_xpath_result(ROOT_URL, '//div[@class="information di-ib mt24"]/a')
character_names = [link.text for link in character_names] character_names = [link.text for link in character_names]