scrape-yuanyuan/shanxi/scrape-articles.py

23 lines
531 B
Python

"""Script to scrape article text from http://sxwjw.shaanxi.gov.cn.
Article contents are in a div with the class `message-box`.
"""
from utils.linkutils import read_links
from utils.scrapeutils import download_link_texts
def main():
"""Collect and output article text."""
with open("articles-shanxi/links.csv", "r") as f:
links = read_links(f)
# Broken links
links = links[:254]
download_link_texts(links, "message-box", "articles-shanxi", encoding="UTF-8")
if __name__ == "__main__":
main()