使用Python爬取知乎上的高颜值小姐姐

def get_answers_by_page(page_no):
    offset = page_no * 10
    url = "<answer url>&offset={}&limit=10&sort_by=default&platform=desktop".format(offset)
    headers = {
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36",
    }
    r = requests.get(url, verify=False, headers=headers)
    content = r.content.decode("utf-8")
    data = json.loads(content)
    is_end = data["paging"]["is_end"]
    items = data["data"]
    client = pymongo.MongoClient()
    db = client["beauty"]
    if len(items) > 0:
        db.answers.insert_many(items)
    return is_end

def get_answers():
    page_no = 0
    client = pymongo.MongoClient()
    while True:
        print(page_no)
        is_end = get_answers_by_page(page_no)
        page_no += 1
        if is_end:
            break

def query():
    client = pymongo.MongoClient()
    db = client["beauty"]
    items = db.answers.find({"voteup_count": {"$gte": 100}}).sort([("voteup_count", pymongo.DESCENDING)])
    count = 0

    for item in items:
        content = item["content"]
        vote_num = item["voteup_count"]
        author = item["author"]["name"]
        matched = re.findall(r'data-original="([^"]+)"', content)
        print("> 来自 {}\n".format(item["url"]))
        print("> 作者 {}\n".format(author))
        print("> 赞数 {}\n".format(vote_num))
        img_urls = []
        for img_url in matched:
            if img_url not in img_urls:
                print("![]({})".format(img_url))
                img_urls.append(img_url)
        count += len(img_urls)
        print("\n\n")
    print(count)