小编kin*_*kai的帖子

几天前，当我运行它时，此代码工作正常：

from bs4 import BeautifulSoup
import datetime
import requests

def getWeekMostRead(date):
    nonfiction_page = requests.get("https://www.amazon.com/charts/"+date.isoformat()+"/mostread/nonfiction")
    content = "amazon"+date.isoformat()+"_nonfiction.html"
    with open(content, "w", encoding="utf-8") as nf_file:
        print(nonfiction_page.content, file=nf_file)

    mostRead_nonfiction = BeautifulSoup(nonfiction_page.content, features="html.parser")

    nonfiction = mostRead_nonfiction.find_all("div", class_="kc-horizontal-rank-card")

    mostread = []
    for books in nonfiction:
        if books.find(class_="kc-rank-card-publisher") is None:
            mostread.append((
                books.find(class_="kc-rank-card-title").string.strip(),
                books.find(class_="kc-rank-card-author").string.strip(),
                "",
                books.find(class_="numeric-star-data").small.string.strip()
            ))
        else:
            mostread.append((
                books.find(class_="kc-rank-card-title").string.strip(),
                books.find(class_="kc-rank-card-author").string.strip(),
                books.find(class_="kc-rank-card-publisher").string.strip(),
                books.find(class_="numeric-star-data").small.string.strip()
            ))
    return mostread

mostread = []
date = datetime.date(2020,1,1)
while date >= datetime.date(2015,1,1):
    print("Scraped data from "+date.isoformat())
    mostread.extend(getWeekMostRead(date))
    date -= datetime.timedelta(7)
print("Currently saving scraped …