Created
September 21, 2018 16:04
-
-
Save ymotongpoo/a994268a8daed56e0973a45298604a26 to your computer and use it in GitHub Desktop.
sample scraping script
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
import bs4 | |
import time | |
base_url_format = "https://b-name.jp/赤ちゃん名前辞典/all/{}/?p={}" | |
def start_request(): | |
data = [] | |
hiragana = [chr(i) for i in range(ord('あ'), ord('ん')+1)] | |
for h in hiragana: | |
i = 1 | |
n = 0 | |
while(True): | |
url = base_url_format.format(h, i) | |
resp = requests.get(url) | |
#print(url) | |
soup = bs4.BeautifulSoup(resp.content, 'html.parser') | |
namelist = soup.find(class_='namelist') | |
trs = namelist.find_all('tr') | |
if len(trs) == 1: | |
break | |
for tr in trs: | |
cellname = tr.find(class_='cell-name') | |
cellyomi = tr.find(class_='cell-yomi') | |
gender = None | |
if tr.find(class_='icon-woman') is not None: | |
gender = '女' | |
elif tr.find(class_='icon-man') is not None: | |
gender = '男' | |
if cellname is not None: | |
print(n, gender, cellname.string, cellyomi.string) | |
n += 1 | |
time.sleep(5) | |
i += 1 | |
def main(): | |
start_request() | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment