Created
August 25, 2021 08:17
-
-
Save Nanguage/a0b3f156df2034d381c260352131e4cc to your computer and use it in GitHub Desktop.
crawl nature's open access articles html and peer review file links
This file contains 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 typing as t | |
from pathlib import Path | |
import fire | |
import mechanicalsoup | |
from bs4 import BeautifulSoup | |
from tqdm import tqdm | |
browser = mechanicalsoup.StatefulBrowser() | |
base_urls = { | |
"Nature": "https://www.nature.com" | |
} | |
page_temps = { | |
"NC": "{base_url}/ncomms/research-articles?searchType=journalSearch&sort=PubDate&page={page_id}" | |
} | |
def get_article_urls(page, base=base_urls['Nature'], item_class="c-card__link u-link-inherit"): | |
urls_relative = [a.attrs['href'] for a in page.find_all("a", class_=item_class)] | |
urls = [base + u for u in urls_relative] | |
return urls | |
def fetch_article_url_list(page_range="1-100", base=base_urls['Nature'], temp=page_temps['NC']): | |
start, end = [int(i) for i in page_range.split('-')] | |
prange = range(start, end+1) | |
urls = [] | |
for page_id in prange: | |
page_url = temp.format(base_url=base, page_id=page_id) | |
browser.open(page_url) | |
page = browser.page | |
urls_page = get_article_urls(page, base) | |
urls += urls_page | |
for u in urls_page: | |
print(u) | |
return urls | |
def crawl_articles(urls: t.Union[str, t.List[str]], store_dir="./articles"): | |
"""Crawl article pages. | |
:param urls: Path to file which store article urls, or a list of article urls. | |
:param store_dir: Path to directory for store results. | |
""" | |
store_path = Path(store_dir) | |
if not store_path.exists(): | |
store_path.mkdir() | |
if type(urls) is str: | |
with open(urls) as f: | |
urls = [line.strip() for line in f] | |
for url in tqdm(urls): | |
browser.open(url) | |
page = browser.page | |
page_id = url.strip(".html").split('/')[-1] | |
out_f = store_path / (page_id + ".html") | |
with open(out_f, 'w') as f: | |
f.write(str(page)) | |
def extract_peer_review_links(html_dir: str): | |
dir_html = Path(html_dir) | |
htmls = dir_html.glob("*.html") | |
for path in htmls: | |
with open(path) as f: | |
content = f.read() | |
soup = BeautifulSoup(content, "html.parser") | |
pv_links = soup.find_all("a", string="Peer Review File") | |
if len(pv_links) == 0: | |
continue | |
pv_link = pv_links[0].attrs['href'] | |
page_id = str(path).strip(".html").split('/')[-1] | |
print(page_id, pv_link, sep="\t") | |
if __name__ == "__main__": | |
fire.Fire() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment