zhihuSpider.py 文件源码

def get_all_pic_url(question_num, answer_offset,answer_limit):
    url = 'https://www.zhihu.com/api/v4/questions/{qnum}/answers?include=data%5B*%5D.is_normal%2Cis_collapsed%2Cannotation_action%' \
          '2Cannotation_detail%2Ccollapse_reason%2Cis_sticky%2Ccollapsed_by%2Csuggest_edit%2Ccomment_count%2Ccan_comment%2Ccontent%2Ceditable_content%2Cvoteup_count%2Creshipment_settings%2Ccomment_permission%' \
          '2Cmark_infos%2Ccreated_time%2Cupdated_time%2Creview_info%2Crelationship.is_authorized%2Cis_author%2Cvoting%2Cis_thanked%2Cis_nothelp%2Cupvoted_followees%3Bdata%5B*%5D.author.follower_count%2Cbadge%5B%3F(type%3Dbest_answerer)%5D.topics&' \
          'offset={offset}&limit={limit}&sort_by=default'
    response = session.get(url.format(qnum=question_num,offset=answer_offset,limit=answer_limit), headers=headers, allow_redirects=False)

    print('json_response', response)
    json_response = response.json()

    answer = json_response['data']
    pattern = re.compile(r'data-original=\"https\:(.*?)\.(jpg|png)"')
    urls = [];
    for i in range(0, len(answer)):
        per_answer_dict = answer[i]  # dict
        per_answer_content_str = per_answer_dict['content']
        match = pattern.findall(per_answer_content_str)
        urls.extend(["https:" + i[0] + ".jpg" for i in match[1::2]])
    return urls