我想验证我的抓取工具从网络获取的链接与我存储在.txt文件中的链接。在我的抓取工具从网络上检索链接后,它会将(' a')附加到我的.txt文件中。但是,如果链接已存在于我的.txt文件中,我想将其附加(' w')。关于我怎么做的任何想法?
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
答案 0 :(得分:0)
如果我正确地解释了您的陈述,您只需要附加字符' a'或者' w'如果链接已存在于文件中,则根据条件将文本文件添加到文本文件中。为此,您可以使用以下代码:
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')