Python-验证，写入和附加.txt文件

Question

I would like to validate the link my crawler gets from the web with the one I stored in my .txt file. After my crawler retrieves links from the web, it will append('a') to my .txt file. However, if the link already exists in my .txt file, I would like to append it with('w'). Any idea on how I can do it?

    def spider(targetname, DOMAIN, g_data):
    for item in g_data:
        try:
            name = item.find_all("strong", {"class": "fullname show-popup-with-id "})[0].text
            username = item.find_all("span", {"class": "username u-dir"})[0].text
            post = item.find_all("p", {"class": "TweetTextSize TweetTextSize--normal js-tweet-text tweet-text"})[0].text
            replies = item.find_all("span", {"class": "u-hiddenVisually"})[3].text
            retweets = item.find_all("span", {"class": "u-hiddenVisually"})[4].text
            likes = item.find_all("span", {"class": "u-hiddenVisually"})[5].text
            retweetby = item.find_all("a", {"href": "/"+targetname})[0].text
            datas = item.find_all('a', {'class':'tweet-timestamp js-permalink js-nav js-tooltip'})
            for data in datas:
                link = DOMAIN + data['href']
                date = data['title']
            append_to_file(crawledfile, name, username, post, link, replies, retweets, likes, retweetby, date)
        except:
            pass


`def append_to_file(path, name, username, post, link, replies, retweets, likes, retweetby, date):
    with open(path, 'a') as file:
        try:
            file.write("Name: "+ name + '\n')
        except:
            print("Name: --Currently unavailable--" + '\n')
        try:
            file.write("Username: "+ username + '\n')
        except:
            print("Username: --Currently unavailable--" + '\n')
        try:
            file.write("Post: "+ post + '\n')
        except:
            print("Post: --Currently unavailable--" + '\n')
        try:
            file.write("post's link: "+ link.strip() + '\n')
        except:
            print("post's link: --Currently unavailable--" + '\n')
        try:
            file.write("Replies: "+ replies.strip() + '\n')
        except:
            print("Replies: --Currently unavailable--" + '\n')
        try:
            file.write("Retweet: "+ retweets.strip() + '\n')
        except:
            print("Retweet: --Currently unavailable--" + '\n')
        try:
            file.write("Likes: "+ likes.strip() + '\n')
        except:
            print("Likes: --Currently unavailable--" + '\n')
        try:
            if(username != "@" + targetname):
                file.write("Retweeted By: " + retweetby.strip() + '\n')
        except:
            file.write("Retweeted By: --Currently unavailable--" + '\n')
        try:
            file.write("Date: " + date + '\n')
        except:
            file.write("Date: --Currently unavailable--" + '\n')
        file.write("" + '\n')`




Name: Donald J. Trump Username: @realDonaldTrump Post: I look forward to paying my respects to our brave men and women on this Memorial Day at Arlington National Cemetery later this morning. post's link: https://twitter.com/realDonaldTrump/status/869170615881793536 Replies: 14,333 replies Retweet: 13,492 retweets Likes: 74,645 likes Date: 5:36 AM - 29 May 2017

Name: Donald J. Trump Username: @realDonaldTrump Post: Today we remember the men and women who made the ultimate sacrifice in serving. Thank you, God bless your families & God bless the USA! post's link: https://twitter.com/realDonaldTrump/status/869170351049240576 Replies: 8,827 replies Retweet: 33,541 retweets Likes: 123,112 likes Date: 5:35 AM - 29 May 2017

Answer 1

If I interpreted your statement correctly, you just need to append the character 'a' or 'w' to your text file based on the condition if the link is already present in the file or not. For this, you can use this code:

def append_to_file(path, name, username, post, link, replies, retweets, likes, retweetby, date):
    with open(path, 'a') as file:
        if link.strip() in file.read():
            to_append = 'a'
        else:
            to_append = 'w'
        try:
            file.write("Name: " + name + to_append + '\n')
        except:
            print("Name: -- Currently unavailable--" + '\n')
        try:
            file.write("Username: " + username + to_append + '\n')
        except:
            print("Username: -- Currently unavailable--" + '\n')
        try:
            file.write("Post: " + post + to_append + '\n')
        except:
            print("Post: -- Currently unavailable--" + '\n')
        try:
            file.write("post's link: " + link.strip() + to_append + '\n')
        except:
            print("post's link: -- Currently unavailable--" + '\n')
        try:
            file.write("Replies: " + replies.strip() + to_append + '\n')
        except:
            print("Replies: -- Currently unavailable--" + '\n')
        try:
            file.write("Retweet: " + retweets.strip() + to_append + '\n')
        except:
            print("Retweet: -- Currently unavailable--" + '\n')
        try:
            file.write("Likes: " + likes.strip() + to_append + '\n')
        except:
            print("Likes: -- Currently unavailable--" + '\n')
        try:
            if(username != "@" + targetname):
                file.write("Retweeted By: " +
                           retweetby.strip() + to_append + '\n')
        except:
            file.write(
                "Retweeted By: -- Currently unavailable--" + '\n')
        try:
            file.write("Date: " + date + to_append + '\n')
        except:
            file.write("Date: -- Currently unavailable--" +
                       to_append + '\n')
        file.write("" + '\n')